Merge pull request #9593 from hashicorp/azr-docs-extractor
add snippet-extractor for documentation
This commit is contained in:
Megan Marsh
GitHub
commit
6cdfdcc3c5
|
|
@ -1,89 +0,0 @@
|
|||
package main
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"io/ioutil"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"regexp"
|
||||
"strings"
|
||||
|
||||
"github.com/gocolly/colly"
|
||||
)
|
||||
|
||||
const (
|
||||
DocsUrl = "http://127.0.0.1:4567/docs/"
|
||||
CacheDir = "cache/"
|
||||
)
|
||||
|
||||
func commentize(text string) string {
|
||||
text = text[strings.Index(text, ") -")+len(") -"):]
|
||||
text = strings.ReplaceAll(text, "\n", "\n // ")
|
||||
return text
|
||||
}
|
||||
|
||||
func main() {
|
||||
c := colly.NewCollector()
|
||||
|
||||
// Find and visit all doc pages
|
||||
c.OnHTML("a[href]", func(e *colly.HTMLElement) {
|
||||
url := e.Attr("href")
|
||||
if !strings.HasPrefix(url, "/docs/builders") {
|
||||
return
|
||||
}
|
||||
e.Request.Visit(url)
|
||||
})
|
||||
for _, required := range []bool{true, false} {
|
||||
required := required
|
||||
sel := "#required- + ul a[name]"
|
||||
if !required {
|
||||
sel = "#optional- + ul a[name]"
|
||||
}
|
||||
c.OnHTML(sel, func(e *colly.HTMLElement) {
|
||||
|
||||
name := e.Attr("name")
|
||||
|
||||
builder := e.Request.URL.Path[strings.Index(e.Request.URL.Path, "/builders/")+len("/builders/"):]
|
||||
builder = strings.TrimSuffix(builder, ".html")
|
||||
|
||||
fieldDoc := e.DOM.Parent()
|
||||
text := fieldDoc.Text()
|
||||
|
||||
builderPath := strings.Split(builder, "-")[0]
|
||||
if name == "vpc_filter" {
|
||||
fmt.Printf("required: %25s builderPath: %20s text: %20s\n", name, builderPath, text)
|
||||
}
|
||||
|
||||
err := filepath.Walk("./builder/"+builderPath, func(path string, info os.FileInfo, err error) error {
|
||||
if err != nil || info.IsDir() || filepath.Ext(path) != ".go" {
|
||||
return nil
|
||||
}
|
||||
body, err := ioutil.ReadFile(path)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
regex := regexp.MustCompile(fmt.Sprintf(`(\n\s+//.*)*\n+(\s*)([A-Z].*mapstructure:"%s")(\s+required:"%t")?(.*)`, name, required))
|
||||
|
||||
replaced := regex.ReplaceAll(body, []byte(fmt.Sprintf("\n$2//%s\n"+`$2$3 required:"%t"$5`, commentize(text), required)))
|
||||
|
||||
if string(replaced) == string(body) {
|
||||
return nil
|
||||
}
|
||||
|
||||
err = ioutil.WriteFile(path, replaced, 0)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
|
||||
return nil
|
||||
})
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
c.CacheDir = CacheDir
|
||||
|
||||
c.Visit(DocsUrl)
|
||||
}
|
||||
|
|
@ -0,0 +1,146 @@
|
|||
// snippet-extract --begin=#_BEGIN_WRAP_TAG_ --end=#_END_WRAP_TAG_ -output_dir=./docs/ [./file|./directory/]...
|
||||
// Extracts markdown snippets from relative files into output_dir, keeping the
|
||||
// directory layout.
|
||||
// It is not mandatory to terminate a snippet, the extractor will simply add
|
||||
// line until EOF.
|
||||
// Lines matching begin or end tags will not be put in the resulting file.
|
||||
// When a directory is passed, all files from directory will be parsed.
|
||||
package main
|
||||
|
||||
import (
|
||||
"bufio"
|
||||
"bytes"
|
||||
"flag"
|
||||
"fmt"
|
||||
"io/ioutil"
|
||||
"log"
|
||||
"os"
|
||||
"path/filepath"
|
||||
"strings"
|
||||
)
|
||||
|
||||
type options struct {
|
||||
filenames []string
|
||||
begin, end string
|
||||
outputDir string
|
||||
extension string
|
||||
}
|
||||
|
||||
func (o *options) AddFlagSets(fs *flag.FlagSet) {
|
||||
fs.StringVar(&o.begin, "begin", "#_BEGIN_WRAP_TAG_", "flag to mark beginning of a snippet")
|
||||
fs.StringVar(&o.end, "end", "#_END_WRAP_TAG_", "flag to mark ending of a snippet")
|
||||
fs.StringVar(&o.outputDir, "output_dir", "./docs/", "directory in which the files will be generated, note that the directory layout is kept")
|
||||
fs.StringVar(&o.extension, "extension", ".mdx", "extension for generated files")
|
||||
}
|
||||
|
||||
func main() {
|
||||
fs := flag.NewFlagSet("snippet-extract", flag.ContinueOnError)
|
||||
opts := options{}
|
||||
opts.AddFlagSets(fs)
|
||||
if err := fs.Parse(os.Args[1:]); err != nil {
|
||||
fs.Usage()
|
||||
os.Exit(1)
|
||||
}
|
||||
wd, _ := os.Getwd()
|
||||
fmt.Printf("working from %s\n", wd)
|
||||
opts.filenames = extactFilenames(fs.Args())
|
||||
for _, filename := range opts.filenames {
|
||||
ext := filepath.Ext(filename)
|
||||
snippets := extractSnippets(opts.begin, opts.end, filename)
|
||||
for _, snippet := range snippets {
|
||||
outputFile := filepath.Join(opts.outputDir, filepath.Base(filename), snippet.Identifier+opts.extension)
|
||||
folder := filepath.Dir(outputFile)
|
||||
err := os.MkdirAll(folder, os.ModePerm)
|
||||
if err != nil {
|
||||
log.Printf("cannot mkdir %s: %s", folder, err)
|
||||
}
|
||||
f := bytes.NewBuffer(nil)
|
||||
fmt.Fprintf(f, `<!-- Code generated by snippet-extractor %s; DO NOT EDIT MANUALLY -->`, strings.Join(os.Args[1:], " "))
|
||||
fmt.Fprintf(f, "\n\n```%s\n%s```\n", ext, snippet.Text)
|
||||
err = ioutil.WriteFile(outputFile, f.Bytes(), 0600)
|
||||
if err != nil {
|
||||
log.Printf("cannot write %s in %s: %s", filepath.Base(outputFile), folder, err)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
type snippet struct {
|
||||
Identifier string
|
||||
Text string
|
||||
Closed bool
|
||||
}
|
||||
|
||||
func extractSnippets(beginPattern, endPattern, filename string) []snippet {
|
||||
file, err := os.Open(filename)
|
||||
if err != nil {
|
||||
log.Printf("could not open file: %s", err)
|
||||
os.Exit(1)
|
||||
}
|
||||
defer file.Close()
|
||||
|
||||
scanner := bufio.NewScanner(file)
|
||||
|
||||
snippets := []snippet{}
|
||||
for scanner.Scan() {
|
||||
line := scanner.Text()
|
||||
if identifier := matches(line, beginPattern); identifier != "" {
|
||||
snippets = append(snippets, snippet{
|
||||
Identifier: identifier,
|
||||
})
|
||||
continue
|
||||
}
|
||||
if identifier := matches(line, endPattern); identifier != "" {
|
||||
for i := range snippets {
|
||||
snippet := &snippets[i]
|
||||
if snippet.Identifier == identifier {
|
||||
snippet.Closed = true
|
||||
}
|
||||
}
|
||||
continue
|
||||
}
|
||||
for i := range snippets {
|
||||
snippet := &snippets[i]
|
||||
if snippet.Closed {
|
||||
continue
|
||||
}
|
||||
snippet.Text = snippet.Text + line + "\n"
|
||||
}
|
||||
}
|
||||
return snippets
|
||||
}
|
||||
|
||||
func matches(s, prefix string) string {
|
||||
trimmed := strings.TrimSpace(s)
|
||||
lenDiff := len(s) - len(trimmed)
|
||||
if strings.HasPrefix(trimmed, prefix) {
|
||||
return s[len(prefix)+lenDiff:]
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// if an entry is a directory all files from directory will be listed.
|
||||
func extactFilenames(in []string) []string {
|
||||
out := []string{}
|
||||
for _, path := range in {
|
||||
fi, err := os.Stat(path)
|
||||
if err != nil {
|
||||
log.Fatalf("%s: %s", path, err)
|
||||
}
|
||||
if !fi.IsDir() {
|
||||
out = append(out, path)
|
||||
continue
|
||||
}
|
||||
files, err := ioutil.ReadDir(path)
|
||||
if err != nil {
|
||||
log.Fatalf("could not read directory %s: %s", path, err)
|
||||
}
|
||||
for _, file := range files {
|
||||
if file.IsDir() {
|
||||
continue
|
||||
}
|
||||
out = append(out, file.Name())
|
||||
}
|
||||
}
|
||||
return in
|
||||
}
|
||||
7
go.mod
7
go.mod
|
|
@ -12,14 +12,11 @@ require (
|
|||
github.com/Azure/go-ntlmssp v0.0.0-20191115201650-bad6df29494a // indirect
|
||||
github.com/ChrisTrenkamp/goxpath v0.0.0-20170922090931-c385f95c6022
|
||||
github.com/NaverCloudPlatform/ncloud-sdk-go-v2 v1.1.0
|
||||
github.com/PuerkitoBio/goquery v1.5.0 // indirect
|
||||
github.com/StackExchange/wmi v0.0.0-20190523213315-cbe66965904d // indirect
|
||||
github.com/Telmate/proxmox-api-go v0.0.0-20200715182505-ec97c70ba887
|
||||
github.com/abdullin/seq v0.0.0-20160510034733-d5467c17e7af // indirect
|
||||
github.com/aliyun/alibaba-cloud-sdk-go v0.0.0-20190418113227-25233c783f4e
|
||||
github.com/aliyun/aliyun-oss-go-sdk v0.0.0-20170113022742-e6dbea820a9f
|
||||
github.com/antchfx/htmlquery v1.0.0 // indirect
|
||||
github.com/antchfx/xmlquery v1.0.0 // indirect
|
||||
github.com/antchfx/xpath v0.0.0-20170728053731-b5c552e1acbd // indirect
|
||||
github.com/antchfx/xquery v0.0.0-20170730121040-eb8c3c172607 // indirect
|
||||
github.com/approvals/go-approval-tests v0.0.0-20160714161514-ad96e53bea43
|
||||
|
|
@ -45,7 +42,6 @@ require (
|
|||
github.com/go-ole/go-ole v1.2.4 // indirect
|
||||
github.com/go-resty/resty/v2 v2.3.0
|
||||
github.com/gobwas/glob v0.2.3
|
||||
github.com/gocolly/colly v1.2.0
|
||||
github.com/gofrs/flock v0.7.1
|
||||
github.com/golang-collections/collections v0.0.0-20130729185459-604e922904d3
|
||||
github.com/golang/protobuf v1.4.2 // indirect
|
||||
|
|
@ -85,7 +81,6 @@ require (
|
|||
github.com/json-iterator/go v1.1.6 // indirect
|
||||
github.com/jtolds/gls v4.2.1+incompatible // indirect
|
||||
github.com/kardianos/osext v0.0.0-20170510131534-ae77be60afb1
|
||||
github.com/kennygrant/sanitize v1.2.4 // indirect
|
||||
github.com/klauspost/compress v0.0.0-20160131094358-f86d2e6d8a77 // indirect
|
||||
github.com/klauspost/cpuid v0.0.0-20160106104451-349c67577817 // indirect
|
||||
github.com/klauspost/crc32 v0.0.0-20160114101742-999f3125931f // indirect
|
||||
|
|
@ -120,7 +115,6 @@ require (
|
|||
github.com/posener/complete v1.2.3
|
||||
github.com/profitbricks/profitbricks-sdk-go v4.0.2+incompatible
|
||||
github.com/renstrom/fuzzysearch v0.0.0-20160331204855-2d205ac6ec17 // indirect
|
||||
github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca // indirect
|
||||
github.com/satori/go.uuid v1.2.0 // indirect
|
||||
github.com/scaleway/scaleway-cli v0.0.0-20180921094345-7b12c9699d70
|
||||
github.com/shirou/gopsutil v2.18.12+incompatible
|
||||
|
|
@ -129,7 +123,6 @@ require (
|
|||
github.com/smartystreets/goconvey v0.0.0-20181108003508-044398e4856c // indirect
|
||||
github.com/stretchr/objx v0.2.0 // indirect
|
||||
github.com/stretchr/testify v1.5.1
|
||||
github.com/temoto/robotstxt v1.1.1 // indirect
|
||||
github.com/tencentcloud/tencentcloud-sdk-go v3.0.155+incompatible
|
||||
github.com/ucloud/ucloud-sdk-go v0.16.3
|
||||
github.com/ufilesdk-dev/ufile-gosdk v0.0.0-20190830075812-b4dbc4ef43a6
|
||||
|
|
|
|||
18
go.sum
18
go.sum
|
|
@ -73,8 +73,6 @@ github.com/DataDog/datadog-go v2.2.0+incompatible h1:V5BKkxACZLjzHjSgBbr2gvLA2Ae
|
|||
github.com/DataDog/datadog-go v2.2.0+incompatible/go.mod h1:LButxg5PwREeZtORoXG3tL4fMGNddJ+vMq1mwgfaqoQ=
|
||||
github.com/NaverCloudPlatform/ncloud-sdk-go-v2 v1.1.0 h1:0nxjOH7NurPGUWNG5BCrASWjB0uuhGbgJAKLqj2ZDTo=
|
||||
github.com/NaverCloudPlatform/ncloud-sdk-go-v2 v1.1.0/go.mod h1:P+3VS0ETiQPyWOx3vB/oeC8J3qd7jnVZLYAFwWgGRt8=
|
||||
github.com/PuerkitoBio/goquery v1.5.0 h1:uGvmFXOA73IKluu/F84Xd1tt/z07GYm8X49XKHP7EJk=
|
||||
github.com/PuerkitoBio/goquery v1.5.0/go.mod h1:qD2PgZ9lccMbQlc7eEOjaeRlFQON7xY8kdmcsrnKqMg=
|
||||
github.com/StackExchange/wmi v0.0.0-20190523213315-cbe66965904d h1:G0m3OIz70MZUWq3EgK3CesDbo8upS2Vm9/P3FtgI+Jk=
|
||||
github.com/StackExchange/wmi v0.0.0-20190523213315-cbe66965904d/go.mod h1:3eOhrUMpNV+6aFIbp5/iudMxNCF27Vw2OZgy4xEx0Fg=
|
||||
github.com/Telmate/proxmox-api-go v0.0.0-20200715182505-ec97c70ba887 h1:Q65o4V0g/KR1sSUZIMf4m1rShb7f1tVHuEt30hfnh2A=
|
||||
|
|
@ -87,12 +85,6 @@ github.com/aliyun/alibaba-cloud-sdk-go v0.0.0-20190418113227-25233c783f4e h1:/8w
|
|||
github.com/aliyun/alibaba-cloud-sdk-go v0.0.0-20190418113227-25233c783f4e/go.mod h1:T9M45xf79ahXVelWoOBmH0y4aC1t5kXO5BxwyakgIGA=
|
||||
github.com/aliyun/aliyun-oss-go-sdk v0.0.0-20170113022742-e6dbea820a9f h1:jI4DIE5Vf4oRaHfthB0oRhU+yuYuoOTurDzwAlskP00=
|
||||
github.com/aliyun/aliyun-oss-go-sdk v0.0.0-20170113022742-e6dbea820a9f/go.mod h1:T/Aws4fEfogEE9v+HPhhw+CntffsBHJ8nXQCwKr0/g8=
|
||||
github.com/andybalholm/cascadia v1.0.0 h1:hOCXnnZ5A+3eVDX8pvgl4kofXv2ELss0bKcqRySc45o=
|
||||
github.com/andybalholm/cascadia v1.0.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
|
||||
github.com/antchfx/htmlquery v1.0.0 h1:O5IXz8fZF3B3MW+B33MZWbTHBlYmcfw0BAxgErHuaMA=
|
||||
github.com/antchfx/htmlquery v1.0.0/go.mod h1:MS9yksVSQXls00iXkiMqXr0J+umL/AmxXKuP28SUJM8=
|
||||
github.com/antchfx/xmlquery v1.0.0 h1:YuEPqexGG2opZKNc9JU3Zw6zFXwC47wNcy6/F8oKsrM=
|
||||
github.com/antchfx/xmlquery v1.0.0/go.mod h1:/+CnyD/DzHRnv2eRxrVbieRU/FIF6N0C+7oTtyUtCKk=
|
||||
github.com/antchfx/xpath v0.0.0-20170728053731-b5c552e1acbd h1:S3Fr6QnkpW9VRjiEY4psQHhhbbahASuNVj52YIce7lI=
|
||||
github.com/antchfx/xpath v0.0.0-20170728053731-b5c552e1acbd/go.mod h1:Yee4kTMuNiPYJ7nSNorELQMr1J33uOpXDMByNYhvtNk=
|
||||
github.com/antchfx/xquery v0.0.0-20170730121040-eb8c3c172607 h1:BFFG6KP8ASFBg2ptWsJn8p8RDufBjBDKIxLU7BTYGOM=
|
||||
|
|
@ -216,8 +208,6 @@ github.com/go-test/deep v1.0.3 h1:ZrJSEWsXzPOxaZnFteGEfooLba+ju3FYIbOrS+rQd68=
|
|||
github.com/go-test/deep v1.0.3/go.mod h1:wGDj63lr65AM2AQyKZd/NYHGb0R+1RLqB8NKt3aSFNA=
|
||||
github.com/gobwas/glob v0.2.3 h1:A4xDbljILXROh+kObIiy5kIaPYD8e96x1tgBhUI5J+Y=
|
||||
github.com/gobwas/glob v0.2.3/go.mod h1:d3Ez4x06l9bZtSvzIay5+Yzi0fmZzPgnTbPcKjJAkT8=
|
||||
github.com/gocolly/colly v1.2.0 h1:qRz9YAn8FIH0qzgNUw+HT9UN7wm1oF9OBAilwEWpyrI=
|
||||
github.com/gocolly/colly v1.2.0/go.mod h1:Hof5T3ZswNVsOHYmba1u03W65HDWgpV5HifSuueE0EA=
|
||||
github.com/gofrs/uuid v3.2.0+incompatible h1:y12jRkkFxsd7GpqdSZ+/KCs/fJbqpEXSGd4+jfEaewE=
|
||||
github.com/gofrs/uuid v3.2.0+incompatible h1:y12jRkkFxsd7GpqdSZ+/KCs/fJbqpEXSGd4+jfEaewE=
|
||||
github.com/gofrs/uuid v3.2.0+incompatible/go.mod h1:b2aQJv3Z4Fp6yNu3cdSllBxTCLRxnplIgP/c0N/04lM=
|
||||
|
|
@ -416,8 +406,6 @@ github.com/jtolds/gls v4.2.1+incompatible h1:fSuqC+Gmlu6l/ZYAoZzx2pyucC8Xza35fpR
|
|||
github.com/jtolds/gls v4.2.1+incompatible/go.mod h1:QJZ7F/aHp+rZTRtaJ1ow/lLfFfVYBRgL+9YlvaHOwJU=
|
||||
github.com/kardianos/osext v0.0.0-20170510131534-ae77be60afb1 h1:PJPDf8OUfOK1bb/NeTKd4f1QXZItOX389VN3B6qC8ro=
|
||||
github.com/kardianos/osext v0.0.0-20170510131534-ae77be60afb1/go.mod h1:1NbS8ALrpOvjt0rHPNLyCIeMtbizbir8U//inJ+zuB8=
|
||||
github.com/kennygrant/sanitize v1.2.4 h1:gN25/otpP5vAsO2djbMhF/LQX6R7+O1TB4yv8NzpJ3o=
|
||||
github.com/kennygrant/sanitize v1.2.4/go.mod h1:LGsjYYtgxbetdg5owWB2mpgUL6e2nfw2eObZ0u0qvak=
|
||||
github.com/kisielk/errcheck v1.1.0/go.mod h1:EZBBE59ingxPouuu3KfxchcWSUPOHkagtvWXihfKN4Q=
|
||||
github.com/kisielk/gotool v1.0.0/go.mod h1:XhKaO+MFFWcvkIS/tQcRk01m1F5IRFswLeQ+oQHNcck=
|
||||
github.com/klauspost/compress v0.0.0-20160131094358-f86d2e6d8a77 h1:rJnR80lkojFgjdg/oQPhbZoY8t8uM51XMz8DrJrjabk=
|
||||
|
|
@ -566,8 +554,6 @@ github.com/ryanuber/columnize v2.1.0+incompatible h1:j1Wcmh8OrK4Q7GXY+V7SVSY8nUW
|
|||
github.com/ryanuber/columnize v2.1.0+incompatible/go.mod h1:sm1tb6uqfes/u+d4ooFouqFdy9/2g9QGwK3SQygK0Ts=
|
||||
github.com/ryanuber/go-glob v1.0.0 h1:iQh3xXAumdQ+4Ufa5b25cRpC5TYKlno6hsv6Cb3pkBk=
|
||||
github.com/ryanuber/go-glob v1.0.0/go.mod h1:807d1WSdnB0XRJzKNil9Om6lcp/3a0v4qIHxIXzX/Yc=
|
||||
github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca h1:NugYot0LIVPxTvN8n+Kvkn6TrbMyxQiuvKdEwFdR9vI=
|
||||
github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca/go.mod h1:uugorj2VCxiV1x+LzaIdVa9b4S4qGAcH6cbhh4qVxOU=
|
||||
github.com/satori/go.uuid v1.2.0 h1:0uYX9dsZ2yD7q2RtLRtPSdGDWzjeM3TbMJP9utgA0ww=
|
||||
github.com/satori/go.uuid v1.2.0/go.mod h1:dA0hQrYB0VpLJoorglMZABFdXlWrHn1NEOzdhQKdks0=
|
||||
github.com/scaleway/scaleway-cli v0.0.0-20180921094345-7b12c9699d70 h1:DaqC32ZwOuO4ctgg9qAdKnlQxwFPkKmCOEqwSNwYy7c=
|
||||
|
|
@ -603,8 +589,6 @@ github.com/stretchr/testify v1.4.0 h1:2E4SXV/wtOkTonXsotYi4li6zVWxYlZuYNCXe9XRJy
|
|||
github.com/stretchr/testify v1.4.0/go.mod h1:j7eGeouHqKxXV5pUuKE4zz7dFj8WfuZ+81PSLYec5m4=
|
||||
github.com/stretchr/testify v1.5.1 h1:nOGnQDM7FYENwehXlg/kFVnos3rEvtKTjRvOWSzb6H4=
|
||||
github.com/stretchr/testify v1.5.1/go.mod h1:5W2xD1RspED5o8YsWQXVCued0rvSQ+mT+I5cxcmMvtA=
|
||||
github.com/temoto/robotstxt v1.1.1 h1:Gh8RCs8ouX3hRSxxK7B1mO5RFByQ4CmJZDwgom++JaA=
|
||||
github.com/temoto/robotstxt v1.1.1/go.mod h1:+1AmkuG3IYkh1kv0d2qEB9Le88ehNO0zwOr3ujewlOo=
|
||||
github.com/tencentcloud/tencentcloud-sdk-go v3.0.155+incompatible h1:M+Q7+SIBnUZbV0ec+HAOtv2M/wmOUsfjEOpQxM3u4xI=
|
||||
github.com/tencentcloud/tencentcloud-sdk-go v3.0.155+incompatible/go.mod h1:0PfYow01SHPMhKY31xa+EFz2RStxIqj6JFAJS+IkCi4=
|
||||
github.com/tv42/httpunix v0.0.0-20150427012821-b75d8614f926 h1:G3dpKMzFDjgEh2q1Z7zUUtKa8ViPtH+ocF0bE0g00O8=
|
||||
|
|
@ -697,12 +681,10 @@ golang.org/x/mod v0.1.1-0.20191105210325-c90efee705ee/go.mod h1:QqPTAvyqsEbceGzB
|
|||
golang.org/x/mod v0.1.1-0.20191107180719-034126e5016b/go.mod h1:QqPTAvyqsEbceGzBzNggFXnrqF1CaUcvgkdR5Ot7KZg=
|
||||
golang.org/x/mod v0.2.0 h1:KU7oHjnv3XNWfa5COkzUifxZmxp1TyI7ImMXqFxLwvQ=
|
||||
golang.org/x/mod v0.2.0/go.mod h1:s0Qsj1ACt9ePp/hMypM3fl4fZqREWJwdYDEqhRiZZUA=
|
||||
golang.org/x/net v0.0.0-20180218175443-cbe0f9307d01/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
golang.org/x/net v0.0.0-20180724234803-3673e40ba225/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
golang.org/x/net v0.0.0-20180811021610-c39426892332/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
golang.org/x/net v0.0.0-20180826012351-8a410e7b638d/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
golang.org/x/net v0.0.0-20181023162649-9b4f9f5ad519/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
golang.org/x/net v0.0.0-20181201002055-351d144fa1fc h1:a3CU5tJYVj92DY2LaA1kUkrsqD5/3mLDhx2NcNqyW+0=
|
||||
golang.org/x/net v0.0.0-20181201002055-351d144fa1fc/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
golang.org/x/net v0.0.0-20190108225652-1e06a53dbb7e/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
|
|
|
|||
|
|
@ -1 +0,0 @@
|
|||
testdata/* linguist-vendored
|
||||
|
|
@ -1,16 +0,0 @@
|
|||
# editor temporary files
|
||||
*.sublime-*
|
||||
.DS_Store
|
||||
*.swp
|
||||
#*.*#
|
||||
tags
|
||||
|
||||
# direnv config
|
||||
.env*
|
||||
|
||||
# test binaries
|
||||
*.test
|
||||
|
||||
# coverage and profilte outputs
|
||||
*.out
|
||||
|
||||
|
|
@ -1,16 +0,0 @@
|
|||
language: go
|
||||
|
||||
go:
|
||||
- 1.1
|
||||
- 1.2.x
|
||||
- 1.3.x
|
||||
- 1.4.x
|
||||
- 1.5.x
|
||||
- 1.6.x
|
||||
- 1.7.x
|
||||
- 1.8.x
|
||||
- 1.9.x
|
||||
- "1.10.x"
|
||||
- 1.11.x
|
||||
- tip
|
||||
|
||||
|
|
@ -1,12 +0,0 @@
|
|||
Copyright (c) 2012-2016, Martin Angers & Contributors
|
||||
All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without modification, are permitted provided that the following conditions are met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright notice, this list of conditions and the following disclaimer.
|
||||
|
||||
* Redistributions in binary form must reproduce the above copyright notice, this list of conditions and the following disclaimer in the documentation and/or other materials provided with the distribution.
|
||||
|
||||
* Neither the name of the author nor the names of its contributors may be used to endorse or promote products derived from this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
|
@ -1,179 +0,0 @@
|
|||
# goquery - a little like that j-thing, only in Go
|
||||
[](http://travis-ci.org/PuerkitoBio/goquery) [](http://godoc.org/github.com/PuerkitoBio/goquery) [](https://sourcegraph.com/github.com/PuerkitoBio/goquery?badge)
|
||||
|
||||
goquery brings a syntax and a set of features similar to [jQuery][] to the [Go language][go]. It is based on Go's [net/html package][html] and the CSS Selector library [cascadia][]. Since the net/html parser returns nodes, and not a full-featured DOM tree, jQuery's stateful manipulation functions (like height(), css(), detach()) have been left off.
|
||||
|
||||
Also, because the net/html parser requires UTF-8 encoding, so does goquery: it is the caller's responsibility to ensure that the source document provides UTF-8 encoded HTML. See the [wiki][] for various options to do this.
|
||||
|
||||
Syntax-wise, it is as close as possible to jQuery, with the same function names when possible, and that warm and fuzzy chainable interface. jQuery being the ultra-popular library that it is, I felt that writing a similar HTML-manipulating library was better to follow its API than to start anew (in the same spirit as Go's `fmt` package), even though some of its methods are less than intuitive (looking at you, [index()][index]...).
|
||||
|
||||
## Table of Contents
|
||||
|
||||
* [Installation](#installation)
|
||||
* [Changelog](#changelog)
|
||||
* [API](#api)
|
||||
* [Examples](#examples)
|
||||
* [Related Projects](#related-projects)
|
||||
* [Support](#support)
|
||||
* [License](#license)
|
||||
|
||||
## Installation
|
||||
|
||||
Please note that because of the net/html dependency, goquery requires Go1.1+.
|
||||
|
||||
$ go get github.com/PuerkitoBio/goquery
|
||||
|
||||
(optional) To run unit tests:
|
||||
|
||||
$ cd $GOPATH/src/github.com/PuerkitoBio/goquery
|
||||
$ go test
|
||||
|
||||
(optional) To run benchmarks (warning: it runs for a few minutes):
|
||||
|
||||
$ cd $GOPATH/src/github.com/PuerkitoBio/goquery
|
||||
$ go test -bench=".*"
|
||||
|
||||
## Changelog
|
||||
|
||||
**Note that goquery's API is now stable, and will not break.**
|
||||
|
||||
* **2018-11-15 (v1.5.0)** : Go module support (thanks @Zaba505).
|
||||
* **2018-06-07 (v1.4.1)** : Add `NewDocumentFromReader` examples.
|
||||
* **2018-03-24 (v1.4.0)** : Deprecate `NewDocument(url)` and `NewDocumentFromResponse(response)`.
|
||||
* **2018-01-28 (v1.3.0)** : Add `ToEnd` constant to `Slice` until the end of the selection (thanks to @davidjwilkins for raising the issue).
|
||||
* **2018-01-11 (v1.2.0)** : Add `AddBack*` and deprecate `AndSelf` (thanks to @davidjwilkins).
|
||||
* **2017-02-12 (v1.1.0)** : Add `SetHtml` and `SetText` (thanks to @glebtv).
|
||||
* **2016-12-29 (v1.0.2)** : Optimize allocations for `Selection.Text` (thanks to @radovskyb).
|
||||
* **2016-08-28 (v1.0.1)** : Optimize performance for large documents.
|
||||
* **2016-07-27 (v1.0.0)** : Tag version 1.0.0.
|
||||
* **2016-06-15** : Invalid selector strings internally compile to a `Matcher` implementation that never matches any node (instead of a panic). So for example, `doc.Find("~")` returns an empty `*Selection` object.
|
||||
* **2016-02-02** : Add `NodeName` utility function similar to the DOM's `nodeName` property. It returns the tag name of the first element in a selection, and other relevant values of non-element nodes (see godoc for details). Add `OuterHtml` utility function similar to the DOM's `outerHTML` property (named `OuterHtml` in small caps for consistency with the existing `Html` method on the `Selection`).
|
||||
* **2015-04-20** : Add `AttrOr` helper method to return the attribute's value or a default value if absent. Thanks to [piotrkowalczuk][piotr].
|
||||
* **2015-02-04** : Add more manipulation functions - Prepend* - thanks again to [Andrew Stone][thatguystone].
|
||||
* **2014-11-28** : Add more manipulation functions - ReplaceWith*, Wrap* and Unwrap - thanks again to [Andrew Stone][thatguystone].
|
||||
* **2014-11-07** : Add manipulation functions (thanks to [Andrew Stone][thatguystone]) and `*Matcher` functions, that receive compiled cascadia selectors instead of selector strings, thus avoiding potential panics thrown by goquery via `cascadia.MustCompile` calls. This results in better performance (selectors can be compiled once and reused) and more idiomatic error handling (you can handle cascadia's compilation errors, instead of recovering from panics, which had been bugging me for a long time). Note that the actual type expected is a `Matcher` interface, that `cascadia.Selector` implements. Other matcher implementations could be used.
|
||||
* **2014-11-06** : Change import paths of net/html to golang.org/x/net/html (see https://groups.google.com/forum/#!topic/golang-nuts/eD8dh3T9yyA). Make sure to update your code to use the new import path too when you call goquery with `html.Node`s.
|
||||
* **v0.3.2** : Add `NewDocumentFromReader()` (thanks jweir) which allows creating a goquery document from an io.Reader.
|
||||
* **v0.3.1** : Add `NewDocumentFromResponse()` (thanks assassingj) which allows creating a goquery document from an http response.
|
||||
* **v0.3.0** : Add `EachWithBreak()` which allows to break out of an `Each()` loop by returning false. This function was added instead of changing the existing `Each()` to avoid breaking compatibility.
|
||||
* **v0.2.1** : Make go-getable, now that [go.net/html is Go1.0-compatible][gonet] (thanks to @matrixik for pointing this out).
|
||||
* **v0.2.0** : Add support for negative indices in Slice(). **BREAKING CHANGE** `Document.Root` is removed, `Document` is now a `Selection` itself (a selection of one, the root element, just like `Document.Root` was before). Add jQuery's Closest() method.
|
||||
* **v0.1.1** : Add benchmarks to use as baseline for refactorings, refactor Next...() and Prev...() methods to use the new html package's linked list features (Next/PrevSibling, FirstChild). Good performance boost (40+% in some cases).
|
||||
* **v0.1.0** : Initial release.
|
||||
|
||||
## API
|
||||
|
||||
goquery exposes two structs, `Document` and `Selection`, and the `Matcher` interface. Unlike jQuery, which is loaded as part of a DOM document, and thus acts on its containing document, goquery doesn't know which HTML document to act upon. So it needs to be told, and that's what the `Document` type is for. It holds the root document node as the initial Selection value to manipulate.
|
||||
|
||||
jQuery often has many variants for the same function (no argument, a selector string argument, a jQuery object argument, a DOM element argument, ...). Instead of exposing the same features in goquery as a single method with variadic empty interface arguments, statically-typed signatures are used following this naming convention:
|
||||
|
||||
* When the jQuery equivalent can be called with no argument, it has the same name as jQuery for the no argument signature (e.g.: `Prev()`), and the version with a selector string argument is called `XxxFiltered()` (e.g.: `PrevFiltered()`)
|
||||
* When the jQuery equivalent **requires** one argument, the same name as jQuery is used for the selector string version (e.g.: `Is()`)
|
||||
* The signatures accepting a jQuery object as argument are defined in goquery as `XxxSelection()` and take a `*Selection` object as argument (e.g.: `FilterSelection()`)
|
||||
* The signatures accepting a DOM element as argument in jQuery are defined in goquery as `XxxNodes()` and take a variadic argument of type `*html.Node` (e.g.: `FilterNodes()`)
|
||||
* The signatures accepting a function as argument in jQuery are defined in goquery as `XxxFunction()` and take a function as argument (e.g.: `FilterFunction()`)
|
||||
* The goquery methods that can be called with a selector string have a corresponding version that take a `Matcher` interface and are defined as `XxxMatcher()` (e.g.: `IsMatcher()`)
|
||||
|
||||
Utility functions that are not in jQuery but are useful in Go are implemented as functions (that take a `*Selection` as parameter), to avoid a potential naming clash on the `*Selection`'s methods (reserved for jQuery-equivalent behaviour).
|
||||
|
||||
The complete [godoc reference documentation can be found here][doc].
|
||||
|
||||
Please note that Cascadia's selectors do not necessarily match all supported selectors of jQuery (Sizzle). See the [cascadia project][cascadia] for details. Invalid selector strings compile to a `Matcher` that fails to match any node. Behaviour of the various functions that take a selector string as argument follows from that fact, e.g. (where `~` is an invalid selector string):
|
||||
|
||||
* `Find("~")` returns an empty selection because the selector string doesn't match anything.
|
||||
* `Add("~")` returns a new selection that holds the same nodes as the original selection, because it didn't add any node (selector string didn't match anything).
|
||||
* `ParentsFiltered("~")` returns an empty selection because the selector string doesn't match anything.
|
||||
* `ParentsUntil("~")` returns all parents of the selection because the selector string didn't match any element to stop before the top element.
|
||||
|
||||
## Examples
|
||||
|
||||
See some tips and tricks in the [wiki][].
|
||||
|
||||
Adapted from example_test.go:
|
||||
|
||||
```Go
|
||||
package main
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"log"
|
||||
"net/http"
|
||||
|
||||
"github.com/PuerkitoBio/goquery"
|
||||
)
|
||||
|
||||
func ExampleScrape() {
|
||||
// Request the HTML page.
|
||||
res, err := http.Get("http://metalsucks.net")
|
||||
if err != nil {
|
||||
log.Fatal(err)
|
||||
}
|
||||
defer res.Body.Close()
|
||||
if res.StatusCode != 200 {
|
||||
log.Fatalf("status code error: %d %s", res.StatusCode, res.Status)
|
||||
}
|
||||
|
||||
// Load the HTML document
|
||||
doc, err := goquery.NewDocumentFromReader(res.Body)
|
||||
if err != nil {
|
||||
log.Fatal(err)
|
||||
}
|
||||
|
||||
// Find the review items
|
||||
doc.Find(".sidebar-reviews article .content-block").Each(func(i int, s *goquery.Selection) {
|
||||
// For each item found, get the band and title
|
||||
band := s.Find("a").Text()
|
||||
title := s.Find("i").Text()
|
||||
fmt.Printf("Review %d: %s - %s\n", i, band, title)
|
||||
})
|
||||
}
|
||||
|
||||
func main() {
|
||||
ExampleScrape()
|
||||
}
|
||||
```
|
||||
|
||||
## Related Projects
|
||||
|
||||
- [Goq][goq], an HTML deserialization and scraping library based on goquery and struct tags.
|
||||
- [andybalholm/cascadia][cascadia], the CSS selector library used by goquery.
|
||||
- [suntong/cascadia][cascadiacli], a command-line interface to the cascadia CSS selector library, useful to test selectors.
|
||||
- [asciimoo/colly](https://github.com/asciimoo/colly), a lightning fast and elegant Scraping Framework
|
||||
- [gnulnx/goperf](https://github.com/gnulnx/goperf), a website performance test tool that also fetches static assets.
|
||||
- [MontFerret/ferret](https://github.com/MontFerret/ferret), declarative web scraping.
|
||||
|
||||
## Support
|
||||
|
||||
There are a number of ways you can support the project:
|
||||
|
||||
* Use it, star it, build something with it, spread the word!
|
||||
- If you do build something open-source or otherwise publicly-visible, let me know so I can add it to the [Related Projects](#related-projects) section!
|
||||
* Raise issues to improve the project (note: doc typos and clarifications are issues too!)
|
||||
- Please search existing issues before opening a new one - it may have already been adressed.
|
||||
* Pull requests: please discuss new code in an issue first, unless the fix is really trivial.
|
||||
- Make sure new code is tested.
|
||||
- Be mindful of existing code - PRs that break existing code have a high probability of being declined, unless it fixes a serious issue.
|
||||
|
||||
If you desperately want to send money my way, I have a BuyMeACoffee.com page:
|
||||
|
||||
<a href="https://www.buymeacoffee.com/mna" target="_blank"><img src="https://www.buymeacoffee.com/assets/img/custom_images/orange_img.png" alt="Buy Me A Coffee" style="height: 41px !important;width: 174px !important;box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;-webkit-box-shadow: 0px 3px 2px 0px rgba(190, 190, 190, 0.5) !important;" ></a>
|
||||
|
||||
## License
|
||||
|
||||
The [BSD 3-Clause license][bsd], the same as the [Go language][golic]. Cascadia's license is [here][caslic].
|
||||
|
||||
[jquery]: http://jquery.com/
|
||||
[go]: http://golang.org/
|
||||
[cascadia]: https://github.com/andybalholm/cascadia
|
||||
[cascadiacli]: https://github.com/suntong/cascadia
|
||||
[bsd]: http://opensource.org/licenses/BSD-3-Clause
|
||||
[golic]: http://golang.org/LICENSE
|
||||
[caslic]: https://github.com/andybalholm/cascadia/blob/master/LICENSE
|
||||
[doc]: http://godoc.org/github.com/PuerkitoBio/goquery
|
||||
[index]: http://api.jquery.com/index/
|
||||
[gonet]: https://github.com/golang/net/
|
||||
[html]: http://godoc.org/golang.org/x/net/html
|
||||
[wiki]: https://github.com/PuerkitoBio/goquery/wiki/Tips-and-tricks
|
||||
[thatguystone]: https://github.com/thatguystone
|
||||
[piotr]: https://github.com/piotrkowalczuk
|
||||
[goq]: https://github.com/andrewstuart/goq
|
||||
|
|
@ -1,124 +0,0 @@
|
|||
package goquery
|
||||
|
||||
import (
|
||||
"golang.org/x/net/html"
|
||||
)
|
||||
|
||||
const (
|
||||
maxUint = ^uint(0)
|
||||
maxInt = int(maxUint >> 1)
|
||||
|
||||
// ToEnd is a special index value that can be used as end index in a call
|
||||
// to Slice so that all elements are selected until the end of the Selection.
|
||||
// It is equivalent to passing (*Selection).Length().
|
||||
ToEnd = maxInt
|
||||
)
|
||||
|
||||
// First reduces the set of matched elements to the first in the set.
|
||||
// It returns a new Selection object, and an empty Selection object if the
|
||||
// the selection is empty.
|
||||
func (s *Selection) First() *Selection {
|
||||
return s.Eq(0)
|
||||
}
|
||||
|
||||
// Last reduces the set of matched elements to the last in the set.
|
||||
// It returns a new Selection object, and an empty Selection object if
|
||||
// the selection is empty.
|
||||
func (s *Selection) Last() *Selection {
|
||||
return s.Eq(-1)
|
||||
}
|
||||
|
||||
// Eq reduces the set of matched elements to the one at the specified index.
|
||||
// If a negative index is given, it counts backwards starting at the end of the
|
||||
// set. It returns a new Selection object, and an empty Selection object if the
|
||||
// index is invalid.
|
||||
func (s *Selection) Eq(index int) *Selection {
|
||||
if index < 0 {
|
||||
index += len(s.Nodes)
|
||||
}
|
||||
|
||||
if index >= len(s.Nodes) || index < 0 {
|
||||
return newEmptySelection(s.document)
|
||||
}
|
||||
|
||||
return s.Slice(index, index+1)
|
||||
}
|
||||
|
||||
// Slice reduces the set of matched elements to a subset specified by a range
|
||||
// of indices. The start index is 0-based and indicates the index of the first
|
||||
// element to select. The end index is 0-based and indicates the index at which
|
||||
// the elements stop being selected (the end index is not selected).
|
||||
//
|
||||
// The indices may be negative, in which case they represent an offset from the
|
||||
// end of the selection.
|
||||
//
|
||||
// The special value ToEnd may be specified as end index, in which case all elements
|
||||
// until the end are selected. This works both for a positive and negative start
|
||||
// index.
|
||||
func (s *Selection) Slice(start, end int) *Selection {
|
||||
if start < 0 {
|
||||
start += len(s.Nodes)
|
||||
}
|
||||
if end == ToEnd {
|
||||
end = len(s.Nodes)
|
||||
} else if end < 0 {
|
||||
end += len(s.Nodes)
|
||||
}
|
||||
return pushStack(s, s.Nodes[start:end])
|
||||
}
|
||||
|
||||
// Get retrieves the underlying node at the specified index.
|
||||
// Get without parameter is not implemented, since the node array is available
|
||||
// on the Selection object.
|
||||
func (s *Selection) Get(index int) *html.Node {
|
||||
if index < 0 {
|
||||
index += len(s.Nodes) // Negative index gets from the end
|
||||
}
|
||||
return s.Nodes[index]
|
||||
}
|
||||
|
||||
// Index returns the position of the first element within the Selection object
|
||||
// relative to its sibling elements.
|
||||
func (s *Selection) Index() int {
|
||||
if len(s.Nodes) > 0 {
|
||||
return newSingleSelection(s.Nodes[0], s.document).PrevAll().Length()
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
// IndexSelector returns the position of the first element within the
|
||||
// Selection object relative to the elements matched by the selector, or -1 if
|
||||
// not found.
|
||||
func (s *Selection) IndexSelector(selector string) int {
|
||||
if len(s.Nodes) > 0 {
|
||||
sel := s.document.Find(selector)
|
||||
return indexInSlice(sel.Nodes, s.Nodes[0])
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
// IndexMatcher returns the position of the first element within the
|
||||
// Selection object relative to the elements matched by the matcher, or -1 if
|
||||
// not found.
|
||||
func (s *Selection) IndexMatcher(m Matcher) int {
|
||||
if len(s.Nodes) > 0 {
|
||||
sel := s.document.FindMatcher(m)
|
||||
return indexInSlice(sel.Nodes, s.Nodes[0])
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
// IndexOfNode returns the position of the specified node within the Selection
|
||||
// object, or -1 if not found.
|
||||
func (s *Selection) IndexOfNode(node *html.Node) int {
|
||||
return indexInSlice(s.Nodes, node)
|
||||
}
|
||||
|
||||
// IndexOfSelection returns the position of the first node in the specified
|
||||
// Selection object within this Selection object, or -1 if not found.
|
||||
func (s *Selection) IndexOfSelection(sel *Selection) int {
|
||||
if sel != nil && len(sel.Nodes) > 0 {
|
||||
return indexInSlice(s.Nodes, sel.Nodes[0])
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
|
@ -1,123 +0,0 @@
|
|||
// Copyright (c) 2012-2016, Martin Angers & Contributors
|
||||
// All rights reserved.
|
||||
//
|
||||
// Redistribution and use in source and binary forms, with or without modification,
|
||||
// are permitted provided that the following conditions are met:
|
||||
//
|
||||
// * Redistributions of source code must retain the above copyright notice,
|
||||
// this list of conditions and the following disclaimer.
|
||||
// * Redistributions in binary form must reproduce the above copyright notice,
|
||||
// this list of conditions and the following disclaimer in the documentation and/or
|
||||
// other materials provided with the distribution.
|
||||
// * Neither the name of the author nor the names of its contributors may be used to
|
||||
// endorse or promote products derived from this software without specific prior written permission.
|
||||
//
|
||||
// THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND ANY EXPRESS
|
||||
// OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY
|
||||
// AND FITNESS FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT HOLDER OR
|
||||
// CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
|
||||
// DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
// DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY,
|
||||
// WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY
|
||||
// WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
||||
/*
|
||||
Package goquery implements features similar to jQuery, including the chainable
|
||||
syntax, to manipulate and query an HTML document.
|
||||
|
||||
It brings a syntax and a set of features similar to jQuery to the Go language.
|
||||
It is based on Go's net/html package and the CSS Selector library cascadia.
|
||||
Since the net/html parser returns nodes, and not a full-featured DOM
|
||||
tree, jQuery's stateful manipulation functions (like height(), css(), detach())
|
||||
have been left off.
|
||||
|
||||
Also, because the net/html parser requires UTF-8 encoding, so does goquery: it is
|
||||
the caller's responsibility to ensure that the source document provides UTF-8 encoded HTML.
|
||||
See the repository's wiki for various options on how to do this.
|
||||
|
||||
Syntax-wise, it is as close as possible to jQuery, with the same method names when
|
||||
possible, and that warm and fuzzy chainable interface. jQuery being the
|
||||
ultra-popular library that it is, writing a similar HTML-manipulating
|
||||
library was better to follow its API than to start anew (in the same spirit as
|
||||
Go's fmt package), even though some of its methods are less than intuitive (looking
|
||||
at you, index()...).
|
||||
|
||||
It is hosted on GitHub, along with additional documentation in the README.md
|
||||
file: https://github.com/puerkitobio/goquery
|
||||
|
||||
Please note that because of the net/html dependency, goquery requires Go1.1+.
|
||||
|
||||
The various methods are split into files based on the category of behavior.
|
||||
The three dots (...) indicate that various "overloads" are available.
|
||||
|
||||
* array.go : array-like positional manipulation of the selection.
|
||||
- Eq()
|
||||
- First()
|
||||
- Get()
|
||||
- Index...()
|
||||
- Last()
|
||||
- Slice()
|
||||
|
||||
* expand.go : methods that expand or augment the selection's set.
|
||||
- Add...()
|
||||
- AndSelf()
|
||||
- Union(), which is an alias for AddSelection()
|
||||
|
||||
* filter.go : filtering methods, that reduce the selection's set.
|
||||
- End()
|
||||
- Filter...()
|
||||
- Has...()
|
||||
- Intersection(), which is an alias of FilterSelection()
|
||||
- Not...()
|
||||
|
||||
* iteration.go : methods to loop over the selection's nodes.
|
||||
- Each()
|
||||
- EachWithBreak()
|
||||
- Map()
|
||||
|
||||
* manipulation.go : methods for modifying the document
|
||||
- After...()
|
||||
- Append...()
|
||||
- Before...()
|
||||
- Clone()
|
||||
- Empty()
|
||||
- Prepend...()
|
||||
- Remove...()
|
||||
- ReplaceWith...()
|
||||
- Unwrap()
|
||||
- Wrap...()
|
||||
- WrapAll...()
|
||||
- WrapInner...()
|
||||
|
||||
* property.go : methods that inspect and get the node's properties values.
|
||||
- Attr*(), RemoveAttr(), SetAttr()
|
||||
- AddClass(), HasClass(), RemoveClass(), ToggleClass()
|
||||
- Html()
|
||||
- Length()
|
||||
- Size(), which is an alias for Length()
|
||||
- Text()
|
||||
|
||||
* query.go : methods that query, or reflect, a node's identity.
|
||||
- Contains()
|
||||
- Is...()
|
||||
|
||||
* traversal.go : methods to traverse the HTML document tree.
|
||||
- Children...()
|
||||
- Contents()
|
||||
- Find...()
|
||||
- Next...()
|
||||
- Parent[s]...()
|
||||
- Prev...()
|
||||
- Siblings...()
|
||||
|
||||
* type.go : definition of the types exposed by goquery.
|
||||
- Document
|
||||
- Selection
|
||||
- Matcher
|
||||
|
||||
* utilities.go : definition of helper functions (and not methods on a *Selection)
|
||||
that are not part of jQuery, but are useful to goquery.
|
||||
- NodeName
|
||||
- OuterHtml
|
||||
*/
|
||||
package goquery
|
||||
|
|
@ -1,70 +0,0 @@
|
|||
package goquery
|
||||
|
||||
import "golang.org/x/net/html"
|
||||
|
||||
// Add adds the selector string's matching nodes to those in the current
|
||||
// selection and returns a new Selection object.
|
||||
// The selector string is run in the context of the document of the current
|
||||
// Selection object.
|
||||
func (s *Selection) Add(selector string) *Selection {
|
||||
return s.AddNodes(findWithMatcher([]*html.Node{s.document.rootNode}, compileMatcher(selector))...)
|
||||
}
|
||||
|
||||
// AddMatcher adds the matcher's matching nodes to those in the current
|
||||
// selection and returns a new Selection object.
|
||||
// The matcher is run in the context of the document of the current
|
||||
// Selection object.
|
||||
func (s *Selection) AddMatcher(m Matcher) *Selection {
|
||||
return s.AddNodes(findWithMatcher([]*html.Node{s.document.rootNode}, m)...)
|
||||
}
|
||||
|
||||
// AddSelection adds the specified Selection object's nodes to those in the
|
||||
// current selection and returns a new Selection object.
|
||||
func (s *Selection) AddSelection(sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return s.AddNodes()
|
||||
}
|
||||
return s.AddNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// Union is an alias for AddSelection.
|
||||
func (s *Selection) Union(sel *Selection) *Selection {
|
||||
return s.AddSelection(sel)
|
||||
}
|
||||
|
||||
// AddNodes adds the specified nodes to those in the
|
||||
// current selection and returns a new Selection object.
|
||||
func (s *Selection) AddNodes(nodes ...*html.Node) *Selection {
|
||||
return pushStack(s, appendWithoutDuplicates(s.Nodes, nodes, nil))
|
||||
}
|
||||
|
||||
// AndSelf adds the previous set of elements on the stack to the current set.
|
||||
// It returns a new Selection object containing the current Selection combined
|
||||
// with the previous one.
|
||||
// Deprecated: This function has been deprecated and is now an alias for AddBack().
|
||||
func (s *Selection) AndSelf() *Selection {
|
||||
return s.AddBack()
|
||||
}
|
||||
|
||||
// AddBack adds the previous set of elements on the stack to the current set.
|
||||
// It returns a new Selection object containing the current Selection combined
|
||||
// with the previous one.
|
||||
func (s *Selection) AddBack() *Selection {
|
||||
return s.AddSelection(s.prevSel)
|
||||
}
|
||||
|
||||
// AddBackFiltered reduces the previous set of elements on the stack to those that
|
||||
// match the selector string, and adds them to the current set.
|
||||
// It returns a new Selection object containing the current Selection combined
|
||||
// with the filtered previous one
|
||||
func (s *Selection) AddBackFiltered(selector string) *Selection {
|
||||
return s.AddSelection(s.prevSel.Filter(selector))
|
||||
}
|
||||
|
||||
// AddBackMatcher reduces the previous set of elements on the stack to those that match
|
||||
// the mateher, and adds them to the curernt set.
|
||||
// It returns a new Selection object containing the current Selection combined
|
||||
// with the filtered previous one
|
||||
func (s *Selection) AddBackMatcher(m Matcher) *Selection {
|
||||
return s.AddSelection(s.prevSel.FilterMatcher(m))
|
||||
}
|
||||
|
|
@ -1,163 +0,0 @@
|
|||
package goquery
|
||||
|
||||
import "golang.org/x/net/html"
|
||||
|
||||
// Filter reduces the set of matched elements to those that match the selector string.
|
||||
// It returns a new Selection object for this subset of matching elements.
|
||||
func (s *Selection) Filter(selector string) *Selection {
|
||||
return s.FilterMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// FilterMatcher reduces the set of matched elements to those that match
|
||||
// the given matcher. It returns a new Selection object for this subset
|
||||
// of matching elements.
|
||||
func (s *Selection) FilterMatcher(m Matcher) *Selection {
|
||||
return pushStack(s, winnow(s, m, true))
|
||||
}
|
||||
|
||||
// Not removes elements from the Selection that match the selector string.
|
||||
// It returns a new Selection object with the matching elements removed.
|
||||
func (s *Selection) Not(selector string) *Selection {
|
||||
return s.NotMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// NotMatcher removes elements from the Selection that match the given matcher.
|
||||
// It returns a new Selection object with the matching elements removed.
|
||||
func (s *Selection) NotMatcher(m Matcher) *Selection {
|
||||
return pushStack(s, winnow(s, m, false))
|
||||
}
|
||||
|
||||
// FilterFunction reduces the set of matched elements to those that pass the function's test.
|
||||
// It returns a new Selection object for this subset of elements.
|
||||
func (s *Selection) FilterFunction(f func(int, *Selection) bool) *Selection {
|
||||
return pushStack(s, winnowFunction(s, f, true))
|
||||
}
|
||||
|
||||
// NotFunction removes elements from the Selection that pass the function's test.
|
||||
// It returns a new Selection object with the matching elements removed.
|
||||
func (s *Selection) NotFunction(f func(int, *Selection) bool) *Selection {
|
||||
return pushStack(s, winnowFunction(s, f, false))
|
||||
}
|
||||
|
||||
// FilterNodes reduces the set of matched elements to those that match the specified nodes.
|
||||
// It returns a new Selection object for this subset of elements.
|
||||
func (s *Selection) FilterNodes(nodes ...*html.Node) *Selection {
|
||||
return pushStack(s, winnowNodes(s, nodes, true))
|
||||
}
|
||||
|
||||
// NotNodes removes elements from the Selection that match the specified nodes.
|
||||
// It returns a new Selection object with the matching elements removed.
|
||||
func (s *Selection) NotNodes(nodes ...*html.Node) *Selection {
|
||||
return pushStack(s, winnowNodes(s, nodes, false))
|
||||
}
|
||||
|
||||
// FilterSelection reduces the set of matched elements to those that match a
|
||||
// node in the specified Selection object.
|
||||
// It returns a new Selection object for this subset of elements.
|
||||
func (s *Selection) FilterSelection(sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return pushStack(s, winnowNodes(s, nil, true))
|
||||
}
|
||||
return pushStack(s, winnowNodes(s, sel.Nodes, true))
|
||||
}
|
||||
|
||||
// NotSelection removes elements from the Selection that match a node in the specified
|
||||
// Selection object. It returns a new Selection object with the matching elements removed.
|
||||
func (s *Selection) NotSelection(sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return pushStack(s, winnowNodes(s, nil, false))
|
||||
}
|
||||
return pushStack(s, winnowNodes(s, sel.Nodes, false))
|
||||
}
|
||||
|
||||
// Intersection is an alias for FilterSelection.
|
||||
func (s *Selection) Intersection(sel *Selection) *Selection {
|
||||
return s.FilterSelection(sel)
|
||||
}
|
||||
|
||||
// Has reduces the set of matched elements to those that have a descendant
|
||||
// that matches the selector.
|
||||
// It returns a new Selection object with the matching elements.
|
||||
func (s *Selection) Has(selector string) *Selection {
|
||||
return s.HasSelection(s.document.Find(selector))
|
||||
}
|
||||
|
||||
// HasMatcher reduces the set of matched elements to those that have a descendant
|
||||
// that matches the matcher.
|
||||
// It returns a new Selection object with the matching elements.
|
||||
func (s *Selection) HasMatcher(m Matcher) *Selection {
|
||||
return s.HasSelection(s.document.FindMatcher(m))
|
||||
}
|
||||
|
||||
// HasNodes reduces the set of matched elements to those that have a
|
||||
// descendant that matches one of the nodes.
|
||||
// It returns a new Selection object with the matching elements.
|
||||
func (s *Selection) HasNodes(nodes ...*html.Node) *Selection {
|
||||
return s.FilterFunction(func(_ int, sel *Selection) bool {
|
||||
// Add all nodes that contain one of the specified nodes
|
||||
for _, n := range nodes {
|
||||
if sel.Contains(n) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
})
|
||||
}
|
||||
|
||||
// HasSelection reduces the set of matched elements to those that have a
|
||||
// descendant that matches one of the nodes of the specified Selection object.
|
||||
// It returns a new Selection object with the matching elements.
|
||||
func (s *Selection) HasSelection(sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return s.HasNodes()
|
||||
}
|
||||
return s.HasNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// End ends the most recent filtering operation in the current chain and
|
||||
// returns the set of matched elements to its previous state.
|
||||
func (s *Selection) End() *Selection {
|
||||
if s.prevSel != nil {
|
||||
return s.prevSel
|
||||
}
|
||||
return newEmptySelection(s.document)
|
||||
}
|
||||
|
||||
// Filter based on the matcher, and the indicator to keep (Filter) or
|
||||
// to get rid of (Not) the matching elements.
|
||||
func winnow(sel *Selection, m Matcher, keep bool) []*html.Node {
|
||||
// Optimize if keep is requested
|
||||
if keep {
|
||||
return m.Filter(sel.Nodes)
|
||||
}
|
||||
// Use grep
|
||||
return grep(sel, func(i int, s *Selection) bool {
|
||||
return !m.Match(s.Get(0))
|
||||
})
|
||||
}
|
||||
|
||||
// Filter based on an array of nodes, and the indicator to keep (Filter) or
|
||||
// to get rid of (Not) the matching elements.
|
||||
func winnowNodes(sel *Selection, nodes []*html.Node, keep bool) []*html.Node {
|
||||
if len(nodes)+len(sel.Nodes) < minNodesForSet {
|
||||
return grep(sel, func(i int, s *Selection) bool {
|
||||
return isInSlice(nodes, s.Get(0)) == keep
|
||||
})
|
||||
}
|
||||
|
||||
set := make(map[*html.Node]bool)
|
||||
for _, n := range nodes {
|
||||
set[n] = true
|
||||
}
|
||||
return grep(sel, func(i int, s *Selection) bool {
|
||||
return set[s.Get(0)] == keep
|
||||
})
|
||||
}
|
||||
|
||||
// Filter based on a function test, and the indicator to keep (Filter) or
|
||||
// to get rid of (Not) the matching elements.
|
||||
func winnowFunction(sel *Selection, f func(int, *Selection) bool, keep bool) []*html.Node {
|
||||
return grep(sel, func(i int, s *Selection) bool {
|
||||
return f(i, s) == keep
|
||||
})
|
||||
}
|
||||
|
|
@ -1,6 +0,0 @@
|
|||
module github.com/PuerkitoBio/goquery
|
||||
|
||||
require (
|
||||
github.com/andybalholm/cascadia v1.0.0
|
||||
golang.org/x/net v0.0.0-20181114220301-adae6a3d119a
|
||||
)
|
||||
|
|
@ -1,5 +0,0 @@
|
|||
github.com/andybalholm/cascadia v1.0.0 h1:hOCXnnZ5A+3eVDX8pvgl4kofXv2ELss0bKcqRySc45o=
|
||||
github.com/andybalholm/cascadia v1.0.0/go.mod h1:GsXiBklL0woXo1j/WYWtSYYC4ouU9PqHO0sqidkEA4Y=
|
||||
golang.org/x/net v0.0.0-20180218175443-cbe0f9307d01/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
golang.org/x/net v0.0.0-20181114220301-adae6a3d119a h1:gOpx8G595UYyvj8UK4+OFyY4rx037g3fmfhe5SasG3U=
|
||||
golang.org/x/net v0.0.0-20181114220301-adae6a3d119a/go.mod h1:mL1N/T3taQHkDXs73rZJwtUhF3w3ftmwwsq0BUmARs4=
|
||||
|
|
@ -1,39 +0,0 @@
|
|||
package goquery
|
||||
|
||||
// Each iterates over a Selection object, executing a function for each
|
||||
// matched element. It returns the current Selection object. The function
|
||||
// f is called for each element in the selection with the index of the
|
||||
// element in that selection starting at 0, and a *Selection that contains
|
||||
// only that element.
|
||||
func (s *Selection) Each(f func(int, *Selection)) *Selection {
|
||||
for i, n := range s.Nodes {
|
||||
f(i, newSingleSelection(n, s.document))
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
// EachWithBreak iterates over a Selection object, executing a function for each
|
||||
// matched element. It is identical to Each except that it is possible to break
|
||||
// out of the loop by returning false in the callback function. It returns the
|
||||
// current Selection object.
|
||||
func (s *Selection) EachWithBreak(f func(int, *Selection) bool) *Selection {
|
||||
for i, n := range s.Nodes {
|
||||
if !f(i, newSingleSelection(n, s.document)) {
|
||||
return s
|
||||
}
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
// Map passes each element in the current matched set through a function,
|
||||
// producing a slice of string holding the returned values. The function
|
||||
// f is called for each element in the selection with the index of the
|
||||
// element in that selection starting at 0, and a *Selection that contains
|
||||
// only that element.
|
||||
func (s *Selection) Map(f func(int, *Selection) string) (result []string) {
|
||||
for i, n := range s.Nodes {
|
||||
result = append(result, f(i, newSingleSelection(n, s.document)))
|
||||
}
|
||||
|
||||
return result
|
||||
}
|
||||
|
|
@ -1,574 +0,0 @@
|
|||
package goquery
|
||||
|
||||
import (
|
||||
"strings"
|
||||
|
||||
"golang.org/x/net/html"
|
||||
)
|
||||
|
||||
// After applies the selector from the root document and inserts the matched elements
|
||||
// after the elements in the set of matched elements.
|
||||
//
|
||||
// If one of the matched elements in the selection is not currently in the
|
||||
// document, it's impossible to insert nodes after it, so it will be ignored.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) After(selector string) *Selection {
|
||||
return s.AfterMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// AfterMatcher applies the matcher from the root document and inserts the matched elements
|
||||
// after the elements in the set of matched elements.
|
||||
//
|
||||
// If one of the matched elements in the selection is not currently in the
|
||||
// document, it's impossible to insert nodes after it, so it will be ignored.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) AfterMatcher(m Matcher) *Selection {
|
||||
return s.AfterNodes(m.MatchAll(s.document.rootNode)...)
|
||||
}
|
||||
|
||||
// AfterSelection inserts the elements in the selection after each element in the set of matched
|
||||
// elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) AfterSelection(sel *Selection) *Selection {
|
||||
return s.AfterNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// AfterHtml parses the html and inserts it after the set of matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) AfterHtml(html string) *Selection {
|
||||
return s.AfterNodes(parseHtml(html)...)
|
||||
}
|
||||
|
||||
// AfterNodes inserts the nodes after each element in the set of matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) AfterNodes(ns ...*html.Node) *Selection {
|
||||
return s.manipulateNodes(ns, true, func(sn *html.Node, n *html.Node) {
|
||||
if sn.Parent != nil {
|
||||
sn.Parent.InsertBefore(n, sn.NextSibling)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// Append appends the elements specified by the selector to the end of each element
|
||||
// in the set of matched elements, following those rules:
|
||||
//
|
||||
// 1) The selector is applied to the root document.
|
||||
//
|
||||
// 2) Elements that are part of the document will be moved to the new location.
|
||||
//
|
||||
// 3) If there are multiple locations to append to, cloned nodes will be
|
||||
// appended to all target locations except the last one, which will be moved
|
||||
// as noted in (2).
|
||||
func (s *Selection) Append(selector string) *Selection {
|
||||
return s.AppendMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// AppendMatcher appends the elements specified by the matcher to the end of each element
|
||||
// in the set of matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) AppendMatcher(m Matcher) *Selection {
|
||||
return s.AppendNodes(m.MatchAll(s.document.rootNode)...)
|
||||
}
|
||||
|
||||
// AppendSelection appends the elements in the selection to the end of each element
|
||||
// in the set of matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) AppendSelection(sel *Selection) *Selection {
|
||||
return s.AppendNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// AppendHtml parses the html and appends it to the set of matched elements.
|
||||
func (s *Selection) AppendHtml(html string) *Selection {
|
||||
return s.AppendNodes(parseHtml(html)...)
|
||||
}
|
||||
|
||||
// AppendNodes appends the specified nodes to each node in the set of matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) AppendNodes(ns ...*html.Node) *Selection {
|
||||
return s.manipulateNodes(ns, false, func(sn *html.Node, n *html.Node) {
|
||||
sn.AppendChild(n)
|
||||
})
|
||||
}
|
||||
|
||||
// Before inserts the matched elements before each element in the set of matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) Before(selector string) *Selection {
|
||||
return s.BeforeMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// BeforeMatcher inserts the matched elements before each element in the set of matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) BeforeMatcher(m Matcher) *Selection {
|
||||
return s.BeforeNodes(m.MatchAll(s.document.rootNode)...)
|
||||
}
|
||||
|
||||
// BeforeSelection inserts the elements in the selection before each element in the set of matched
|
||||
// elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) BeforeSelection(sel *Selection) *Selection {
|
||||
return s.BeforeNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// BeforeHtml parses the html and inserts it before the set of matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) BeforeHtml(html string) *Selection {
|
||||
return s.BeforeNodes(parseHtml(html)...)
|
||||
}
|
||||
|
||||
// BeforeNodes inserts the nodes before each element in the set of matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) BeforeNodes(ns ...*html.Node) *Selection {
|
||||
return s.manipulateNodes(ns, false, func(sn *html.Node, n *html.Node) {
|
||||
if sn.Parent != nil {
|
||||
sn.Parent.InsertBefore(n, sn)
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// Clone creates a deep copy of the set of matched nodes. The new nodes will not be
|
||||
// attached to the document.
|
||||
func (s *Selection) Clone() *Selection {
|
||||
ns := newEmptySelection(s.document)
|
||||
ns.Nodes = cloneNodes(s.Nodes)
|
||||
return ns
|
||||
}
|
||||
|
||||
// Empty removes all children nodes from the set of matched elements.
|
||||
// It returns the children nodes in a new Selection.
|
||||
func (s *Selection) Empty() *Selection {
|
||||
var nodes []*html.Node
|
||||
|
||||
for _, n := range s.Nodes {
|
||||
for c := n.FirstChild; c != nil; c = n.FirstChild {
|
||||
n.RemoveChild(c)
|
||||
nodes = append(nodes, c)
|
||||
}
|
||||
}
|
||||
|
||||
return pushStack(s, nodes)
|
||||
}
|
||||
|
||||
// Prepend prepends the elements specified by the selector to each element in
|
||||
// the set of matched elements, following the same rules as Append.
|
||||
func (s *Selection) Prepend(selector string) *Selection {
|
||||
return s.PrependMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// PrependMatcher prepends the elements specified by the matcher to each
|
||||
// element in the set of matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) PrependMatcher(m Matcher) *Selection {
|
||||
return s.PrependNodes(m.MatchAll(s.document.rootNode)...)
|
||||
}
|
||||
|
||||
// PrependSelection prepends the elements in the selection to each element in
|
||||
// the set of matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) PrependSelection(sel *Selection) *Selection {
|
||||
return s.PrependNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// PrependHtml parses the html and prepends it to the set of matched elements.
|
||||
func (s *Selection) PrependHtml(html string) *Selection {
|
||||
return s.PrependNodes(parseHtml(html)...)
|
||||
}
|
||||
|
||||
// PrependNodes prepends the specified nodes to each node in the set of
|
||||
// matched elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) PrependNodes(ns ...*html.Node) *Selection {
|
||||
return s.manipulateNodes(ns, true, func(sn *html.Node, n *html.Node) {
|
||||
// sn.FirstChild may be nil, in which case this functions like
|
||||
// sn.AppendChild()
|
||||
sn.InsertBefore(n, sn.FirstChild)
|
||||
})
|
||||
}
|
||||
|
||||
// Remove removes the set of matched elements from the document.
|
||||
// It returns the same selection, now consisting of nodes not in the document.
|
||||
func (s *Selection) Remove() *Selection {
|
||||
for _, n := range s.Nodes {
|
||||
if n.Parent != nil {
|
||||
n.Parent.RemoveChild(n)
|
||||
}
|
||||
}
|
||||
|
||||
return s
|
||||
}
|
||||
|
||||
// RemoveFiltered removes the set of matched elements by selector.
|
||||
// It returns the Selection of removed nodes.
|
||||
func (s *Selection) RemoveFiltered(selector string) *Selection {
|
||||
return s.RemoveMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// RemoveMatcher removes the set of matched elements.
|
||||
// It returns the Selection of removed nodes.
|
||||
func (s *Selection) RemoveMatcher(m Matcher) *Selection {
|
||||
return s.FilterMatcher(m).Remove()
|
||||
}
|
||||
|
||||
// ReplaceWith replaces each element in the set of matched elements with the
|
||||
// nodes matched by the given selector.
|
||||
// It returns the removed elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) ReplaceWith(selector string) *Selection {
|
||||
return s.ReplaceWithMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// ReplaceWithMatcher replaces each element in the set of matched elements with
|
||||
// the nodes matched by the given Matcher.
|
||||
// It returns the removed elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) ReplaceWithMatcher(m Matcher) *Selection {
|
||||
return s.ReplaceWithNodes(m.MatchAll(s.document.rootNode)...)
|
||||
}
|
||||
|
||||
// ReplaceWithSelection replaces each element in the set of matched elements with
|
||||
// the nodes from the given Selection.
|
||||
// It returns the removed elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) ReplaceWithSelection(sel *Selection) *Selection {
|
||||
return s.ReplaceWithNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// ReplaceWithHtml replaces each element in the set of matched elements with
|
||||
// the parsed HTML.
|
||||
// It returns the removed elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) ReplaceWithHtml(html string) *Selection {
|
||||
return s.ReplaceWithNodes(parseHtml(html)...)
|
||||
}
|
||||
|
||||
// ReplaceWithNodes replaces each element in the set of matched elements with
|
||||
// the given nodes.
|
||||
// It returns the removed elements.
|
||||
//
|
||||
// This follows the same rules as Selection.Append.
|
||||
func (s *Selection) ReplaceWithNodes(ns ...*html.Node) *Selection {
|
||||
s.AfterNodes(ns...)
|
||||
return s.Remove()
|
||||
}
|
||||
|
||||
// SetHtml sets the html content of each element in the selection to
|
||||
// specified html string.
|
||||
func (s *Selection) SetHtml(html string) *Selection {
|
||||
return setHtmlNodes(s, parseHtml(html)...)
|
||||
}
|
||||
|
||||
// SetText sets the content of each element in the selection to specified content.
|
||||
// The provided text string is escaped.
|
||||
func (s *Selection) SetText(text string) *Selection {
|
||||
return s.SetHtml(html.EscapeString(text))
|
||||
}
|
||||
|
||||
// Unwrap removes the parents of the set of matched elements, leaving the matched
|
||||
// elements (and their siblings, if any) in their place.
|
||||
// It returns the original selection.
|
||||
func (s *Selection) Unwrap() *Selection {
|
||||
s.Parent().Each(func(i int, ss *Selection) {
|
||||
// For some reason, jquery allows unwrap to remove the <head> element, so
|
||||
// allowing it here too. Same for <html>. Why it allows those elements to
|
||||
// be unwrapped while not allowing body is a mystery to me.
|
||||
if ss.Nodes[0].Data != "body" {
|
||||
ss.ReplaceWithSelection(ss.Contents())
|
||||
}
|
||||
})
|
||||
|
||||
return s
|
||||
}
|
||||
|
||||
// Wrap wraps each element in the set of matched elements inside the first
|
||||
// element matched by the given selector. The matched child is cloned before
|
||||
// being inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) Wrap(selector string) *Selection {
|
||||
return s.WrapMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// WrapMatcher wraps each element in the set of matched elements inside the
|
||||
// first element matched by the given matcher. The matched child is cloned
|
||||
// before being inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapMatcher(m Matcher) *Selection {
|
||||
return s.wrapNodes(m.MatchAll(s.document.rootNode)...)
|
||||
}
|
||||
|
||||
// WrapSelection wraps each element in the set of matched elements inside the
|
||||
// first element in the given Selection. The element is cloned before being
|
||||
// inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapSelection(sel *Selection) *Selection {
|
||||
return s.wrapNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// WrapHtml wraps each element in the set of matched elements inside the inner-
|
||||
// most child of the given HTML.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapHtml(html string) *Selection {
|
||||
return s.wrapNodes(parseHtml(html)...)
|
||||
}
|
||||
|
||||
// WrapNode wraps each element in the set of matched elements inside the inner-
|
||||
// most child of the given node. The given node is copied before being inserted
|
||||
// into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapNode(n *html.Node) *Selection {
|
||||
return s.wrapNodes(n)
|
||||
}
|
||||
|
||||
func (s *Selection) wrapNodes(ns ...*html.Node) *Selection {
|
||||
s.Each(func(i int, ss *Selection) {
|
||||
ss.wrapAllNodes(ns...)
|
||||
})
|
||||
|
||||
return s
|
||||
}
|
||||
|
||||
// WrapAll wraps a single HTML structure, matched by the given selector, around
|
||||
// all elements in the set of matched elements. The matched child is cloned
|
||||
// before being inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapAll(selector string) *Selection {
|
||||
return s.WrapAllMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// WrapAllMatcher wraps a single HTML structure, matched by the given Matcher,
|
||||
// around all elements in the set of matched elements. The matched child is
|
||||
// cloned before being inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapAllMatcher(m Matcher) *Selection {
|
||||
return s.wrapAllNodes(m.MatchAll(s.document.rootNode)...)
|
||||
}
|
||||
|
||||
// WrapAllSelection wraps a single HTML structure, the first node of the given
|
||||
// Selection, around all elements in the set of matched elements. The matched
|
||||
// child is cloned before being inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapAllSelection(sel *Selection) *Selection {
|
||||
return s.wrapAllNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// WrapAllHtml wraps the given HTML structure around all elements in the set of
|
||||
// matched elements. The matched child is cloned before being inserted into the
|
||||
// document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapAllHtml(html string) *Selection {
|
||||
return s.wrapAllNodes(parseHtml(html)...)
|
||||
}
|
||||
|
||||
func (s *Selection) wrapAllNodes(ns ...*html.Node) *Selection {
|
||||
if len(ns) > 0 {
|
||||
return s.WrapAllNode(ns[0])
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
// WrapAllNode wraps the given node around the first element in the Selection,
|
||||
// making all other nodes in the Selection children of the given node. The node
|
||||
// is cloned before being inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapAllNode(n *html.Node) *Selection {
|
||||
if s.Size() == 0 {
|
||||
return s
|
||||
}
|
||||
|
||||
wrap := cloneNode(n)
|
||||
|
||||
first := s.Nodes[0]
|
||||
if first.Parent != nil {
|
||||
first.Parent.InsertBefore(wrap, first)
|
||||
first.Parent.RemoveChild(first)
|
||||
}
|
||||
|
||||
for c := getFirstChildEl(wrap); c != nil; c = getFirstChildEl(wrap) {
|
||||
wrap = c
|
||||
}
|
||||
|
||||
newSingleSelection(wrap, s.document).AppendSelection(s)
|
||||
|
||||
return s
|
||||
}
|
||||
|
||||
// WrapInner wraps an HTML structure, matched by the given selector, around the
|
||||
// content of element in the set of matched elements. The matched child is
|
||||
// cloned before being inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapInner(selector string) *Selection {
|
||||
return s.WrapInnerMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// WrapInnerMatcher wraps an HTML structure, matched by the given selector,
|
||||
// around the content of element in the set of matched elements. The matched
|
||||
// child is cloned before being inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapInnerMatcher(m Matcher) *Selection {
|
||||
return s.wrapInnerNodes(m.MatchAll(s.document.rootNode)...)
|
||||
}
|
||||
|
||||
// WrapInnerSelection wraps an HTML structure, matched by the given selector,
|
||||
// around the content of element in the set of matched elements. The matched
|
||||
// child is cloned before being inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapInnerSelection(sel *Selection) *Selection {
|
||||
return s.wrapInnerNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// WrapInnerHtml wraps an HTML structure, matched by the given selector, around
|
||||
// the content of element in the set of matched elements. The matched child is
|
||||
// cloned before being inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapInnerHtml(html string) *Selection {
|
||||
return s.wrapInnerNodes(parseHtml(html)...)
|
||||
}
|
||||
|
||||
// WrapInnerNode wraps an HTML structure, matched by the given selector, around
|
||||
// the content of element in the set of matched elements. The matched child is
|
||||
// cloned before being inserted into the document.
|
||||
//
|
||||
// It returns the original set of elements.
|
||||
func (s *Selection) WrapInnerNode(n *html.Node) *Selection {
|
||||
return s.wrapInnerNodes(n)
|
||||
}
|
||||
|
||||
func (s *Selection) wrapInnerNodes(ns ...*html.Node) *Selection {
|
||||
if len(ns) == 0 {
|
||||
return s
|
||||
}
|
||||
|
||||
s.Each(func(i int, s *Selection) {
|
||||
contents := s.Contents()
|
||||
|
||||
if contents.Size() > 0 {
|
||||
contents.wrapAllNodes(ns...)
|
||||
} else {
|
||||
s.AppendNodes(cloneNode(ns[0]))
|
||||
}
|
||||
})
|
||||
|
||||
return s
|
||||
}
|
||||
|
||||
func parseHtml(h string) []*html.Node {
|
||||
// Errors are only returned when the io.Reader returns any error besides
|
||||
// EOF, but strings.Reader never will
|
||||
nodes, err := html.ParseFragment(strings.NewReader(h), &html.Node{Type: html.ElementNode})
|
||||
if err != nil {
|
||||
panic("goquery: failed to parse HTML: " + err.Error())
|
||||
}
|
||||
return nodes
|
||||
}
|
||||
|
||||
func setHtmlNodes(s *Selection, ns ...*html.Node) *Selection {
|
||||
for _, n := range s.Nodes {
|
||||
for c := n.FirstChild; c != nil; c = n.FirstChild {
|
||||
n.RemoveChild(c)
|
||||
}
|
||||
for _, c := range ns {
|
||||
n.AppendChild(cloneNode(c))
|
||||
}
|
||||
}
|
||||
return s
|
||||
}
|
||||
|
||||
// Get the first child that is an ElementNode
|
||||
func getFirstChildEl(n *html.Node) *html.Node {
|
||||
c := n.FirstChild
|
||||
for c != nil && c.Type != html.ElementNode {
|
||||
c = c.NextSibling
|
||||
}
|
||||
return c
|
||||
}
|
||||
|
||||
// Deep copy a slice of nodes.
|
||||
func cloneNodes(ns []*html.Node) []*html.Node {
|
||||
cns := make([]*html.Node, 0, len(ns))
|
||||
|
||||
for _, n := range ns {
|
||||
cns = append(cns, cloneNode(n))
|
||||
}
|
||||
|
||||
return cns
|
||||
}
|
||||
|
||||
// Deep copy a node. The new node has clones of all the original node's
|
||||
// children but none of its parents or siblings.
|
||||
func cloneNode(n *html.Node) *html.Node {
|
||||
nn := &html.Node{
|
||||
Type: n.Type,
|
||||
DataAtom: n.DataAtom,
|
||||
Data: n.Data,
|
||||
Attr: make([]html.Attribute, len(n.Attr)),
|
||||
}
|
||||
|
||||
copy(nn.Attr, n.Attr)
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
nn.AppendChild(cloneNode(c))
|
||||
}
|
||||
|
||||
return nn
|
||||
}
|
||||
|
||||
func (s *Selection) manipulateNodes(ns []*html.Node, reverse bool,
|
||||
f func(sn *html.Node, n *html.Node)) *Selection {
|
||||
|
||||
lasti := s.Size() - 1
|
||||
|
||||
// net.Html doesn't provide document fragments for insertion, so to get
|
||||
// things in the correct order with After() and Prepend(), the callback
|
||||
// needs to be called on the reverse of the nodes.
|
||||
if reverse {
|
||||
for i, j := 0, len(ns)-1; i < j; i, j = i+1, j-1 {
|
||||
ns[i], ns[j] = ns[j], ns[i]
|
||||
}
|
||||
}
|
||||
|
||||
for i, sn := range s.Nodes {
|
||||
for _, n := range ns {
|
||||
if i != lasti {
|
||||
f(sn, cloneNode(n))
|
||||
} else {
|
||||
if n.Parent != nil {
|
||||
n.Parent.RemoveChild(n)
|
||||
}
|
||||
f(sn, n)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return s
|
||||
}
|
||||
|
|
@ -1,275 +0,0 @@
|
|||
package goquery
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"regexp"
|
||||
"strings"
|
||||
|
||||
"golang.org/x/net/html"
|
||||
)
|
||||
|
||||
var rxClassTrim = regexp.MustCompile("[\t\r\n]")
|
||||
|
||||
// Attr gets the specified attribute's value for the first element in the
|
||||
// Selection. To get the value for each element individually, use a looping
|
||||
// construct such as Each or Map method.
|
||||
func (s *Selection) Attr(attrName string) (val string, exists bool) {
|
||||
if len(s.Nodes) == 0 {
|
||||
return
|
||||
}
|
||||
return getAttributeValue(attrName, s.Nodes[0])
|
||||
}
|
||||
|
||||
// AttrOr works like Attr but returns default value if attribute is not present.
|
||||
func (s *Selection) AttrOr(attrName, defaultValue string) string {
|
||||
if len(s.Nodes) == 0 {
|
||||
return defaultValue
|
||||
}
|
||||
|
||||
val, exists := getAttributeValue(attrName, s.Nodes[0])
|
||||
if !exists {
|
||||
return defaultValue
|
||||
}
|
||||
|
||||
return val
|
||||
}
|
||||
|
||||
// RemoveAttr removes the named attribute from each element in the set of matched elements.
|
||||
func (s *Selection) RemoveAttr(attrName string) *Selection {
|
||||
for _, n := range s.Nodes {
|
||||
removeAttr(n, attrName)
|
||||
}
|
||||
|
||||
return s
|
||||
}
|
||||
|
||||
// SetAttr sets the given attribute on each element in the set of matched elements.
|
||||
func (s *Selection) SetAttr(attrName, val string) *Selection {
|
||||
for _, n := range s.Nodes {
|
||||
attr := getAttributePtr(attrName, n)
|
||||
if attr == nil {
|
||||
n.Attr = append(n.Attr, html.Attribute{Key: attrName, Val: val})
|
||||
} else {
|
||||
attr.Val = val
|
||||
}
|
||||
}
|
||||
|
||||
return s
|
||||
}
|
||||
|
||||
// Text gets the combined text contents of each element in the set of matched
|
||||
// elements, including their descendants.
|
||||
func (s *Selection) Text() string {
|
||||
var buf bytes.Buffer
|
||||
|
||||
// Slightly optimized vs calling Each: no single selection object created
|
||||
var f func(*html.Node)
|
||||
f = func(n *html.Node) {
|
||||
if n.Type == html.TextNode {
|
||||
// Keep newlines and spaces, like jQuery
|
||||
buf.WriteString(n.Data)
|
||||
}
|
||||
if n.FirstChild != nil {
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
f(c)
|
||||
}
|
||||
}
|
||||
}
|
||||
for _, n := range s.Nodes {
|
||||
f(n)
|
||||
}
|
||||
|
||||
return buf.String()
|
||||
}
|
||||
|
||||
// Size is an alias for Length.
|
||||
func (s *Selection) Size() int {
|
||||
return s.Length()
|
||||
}
|
||||
|
||||
// Length returns the number of elements in the Selection object.
|
||||
func (s *Selection) Length() int {
|
||||
return len(s.Nodes)
|
||||
}
|
||||
|
||||
// Html gets the HTML contents of the first element in the set of matched
|
||||
// elements. It includes text and comment nodes.
|
||||
func (s *Selection) Html() (ret string, e error) {
|
||||
// Since there is no .innerHtml, the HTML content must be re-created from
|
||||
// the nodes using html.Render.
|
||||
var buf bytes.Buffer
|
||||
|
||||
if len(s.Nodes) > 0 {
|
||||
for c := s.Nodes[0].FirstChild; c != nil; c = c.NextSibling {
|
||||
e = html.Render(&buf, c)
|
||||
if e != nil {
|
||||
return
|
||||
}
|
||||
}
|
||||
ret = buf.String()
|
||||
}
|
||||
|
||||
return
|
||||
}
|
||||
|
||||
// AddClass adds the given class(es) to each element in the set of matched elements.
|
||||
// Multiple class names can be specified, separated by a space or via multiple arguments.
|
||||
func (s *Selection) AddClass(class ...string) *Selection {
|
||||
classStr := strings.TrimSpace(strings.Join(class, " "))
|
||||
|
||||
if classStr == "" {
|
||||
return s
|
||||
}
|
||||
|
||||
tcls := getClassesSlice(classStr)
|
||||
for _, n := range s.Nodes {
|
||||
curClasses, attr := getClassesAndAttr(n, true)
|
||||
for _, newClass := range tcls {
|
||||
if !strings.Contains(curClasses, " "+newClass+" ") {
|
||||
curClasses += newClass + " "
|
||||
}
|
||||
}
|
||||
|
||||
setClasses(n, attr, curClasses)
|
||||
}
|
||||
|
||||
return s
|
||||
}
|
||||
|
||||
// HasClass determines whether any of the matched elements are assigned the
|
||||
// given class.
|
||||
func (s *Selection) HasClass(class string) bool {
|
||||
class = " " + class + " "
|
||||
for _, n := range s.Nodes {
|
||||
classes, _ := getClassesAndAttr(n, false)
|
||||
if strings.Contains(classes, class) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// RemoveClass removes the given class(es) from each element in the set of matched elements.
|
||||
// Multiple class names can be specified, separated by a space or via multiple arguments.
|
||||
// If no class name is provided, all classes are removed.
|
||||
func (s *Selection) RemoveClass(class ...string) *Selection {
|
||||
var rclasses []string
|
||||
|
||||
classStr := strings.TrimSpace(strings.Join(class, " "))
|
||||
remove := classStr == ""
|
||||
|
||||
if !remove {
|
||||
rclasses = getClassesSlice(classStr)
|
||||
}
|
||||
|
||||
for _, n := range s.Nodes {
|
||||
if remove {
|
||||
removeAttr(n, "class")
|
||||
} else {
|
||||
classes, attr := getClassesAndAttr(n, true)
|
||||
for _, rcl := range rclasses {
|
||||
classes = strings.Replace(classes, " "+rcl+" ", " ", -1)
|
||||
}
|
||||
|
||||
setClasses(n, attr, classes)
|
||||
}
|
||||
}
|
||||
|
||||
return s
|
||||
}
|
||||
|
||||
// ToggleClass adds or removes the given class(es) for each element in the set of matched elements.
|
||||
// Multiple class names can be specified, separated by a space or via multiple arguments.
|
||||
func (s *Selection) ToggleClass(class ...string) *Selection {
|
||||
classStr := strings.TrimSpace(strings.Join(class, " "))
|
||||
|
||||
if classStr == "" {
|
||||
return s
|
||||
}
|
||||
|
||||
tcls := getClassesSlice(classStr)
|
||||
|
||||
for _, n := range s.Nodes {
|
||||
classes, attr := getClassesAndAttr(n, true)
|
||||
for _, tcl := range tcls {
|
||||
if strings.Contains(classes, " "+tcl+" ") {
|
||||
classes = strings.Replace(classes, " "+tcl+" ", " ", -1)
|
||||
} else {
|
||||
classes += tcl + " "
|
||||
}
|
||||
}
|
||||
|
||||
setClasses(n, attr, classes)
|
||||
}
|
||||
|
||||
return s
|
||||
}
|
||||
|
||||
func getAttributePtr(attrName string, n *html.Node) *html.Attribute {
|
||||
if n == nil {
|
||||
return nil
|
||||
}
|
||||
|
||||
for i, a := range n.Attr {
|
||||
if a.Key == attrName {
|
||||
return &n.Attr[i]
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Private function to get the specified attribute's value from a node.
|
||||
func getAttributeValue(attrName string, n *html.Node) (val string, exists bool) {
|
||||
if a := getAttributePtr(attrName, n); a != nil {
|
||||
val = a.Val
|
||||
exists = true
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
// Get and normalize the "class" attribute from the node.
|
||||
func getClassesAndAttr(n *html.Node, create bool) (classes string, attr *html.Attribute) {
|
||||
// Applies only to element nodes
|
||||
if n.Type == html.ElementNode {
|
||||
attr = getAttributePtr("class", n)
|
||||
if attr == nil && create {
|
||||
n.Attr = append(n.Attr, html.Attribute{
|
||||
Key: "class",
|
||||
Val: "",
|
||||
})
|
||||
attr = &n.Attr[len(n.Attr)-1]
|
||||
}
|
||||
}
|
||||
|
||||
if attr == nil {
|
||||
classes = " "
|
||||
} else {
|
||||
classes = rxClassTrim.ReplaceAllString(" "+attr.Val+" ", " ")
|
||||
}
|
||||
|
||||
return
|
||||
}
|
||||
|
||||
func getClassesSlice(classes string) []string {
|
||||
return strings.Split(rxClassTrim.ReplaceAllString(" "+classes+" ", " "), " ")
|
||||
}
|
||||
|
||||
func removeAttr(n *html.Node, attrName string) {
|
||||
for i, a := range n.Attr {
|
||||
if a.Key == attrName {
|
||||
n.Attr[i], n.Attr[len(n.Attr)-1], n.Attr =
|
||||
n.Attr[len(n.Attr)-1], html.Attribute{}, n.Attr[:len(n.Attr)-1]
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
func setClasses(n *html.Node, attr *html.Attribute, classes string) {
|
||||
classes = strings.TrimSpace(classes)
|
||||
if classes == "" {
|
||||
removeAttr(n, "class")
|
||||
return
|
||||
}
|
||||
|
||||
attr.Val = classes
|
||||
}
|
||||
|
|
@ -1,49 +0,0 @@
|
|||
package goquery
|
||||
|
||||
import "golang.org/x/net/html"
|
||||
|
||||
// Is checks the current matched set of elements against a selector and
|
||||
// returns true if at least one of these elements matches.
|
||||
func (s *Selection) Is(selector string) bool {
|
||||
return s.IsMatcher(compileMatcher(selector))
|
||||
}
|
||||
|
||||
// IsMatcher checks the current matched set of elements against a matcher and
|
||||
// returns true if at least one of these elements matches.
|
||||
func (s *Selection) IsMatcher(m Matcher) bool {
|
||||
if len(s.Nodes) > 0 {
|
||||
if len(s.Nodes) == 1 {
|
||||
return m.Match(s.Nodes[0])
|
||||
}
|
||||
return len(m.Filter(s.Nodes)) > 0
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// IsFunction checks the current matched set of elements against a predicate and
|
||||
// returns true if at least one of these elements matches.
|
||||
func (s *Selection) IsFunction(f func(int, *Selection) bool) bool {
|
||||
return s.FilterFunction(f).Length() > 0
|
||||
}
|
||||
|
||||
// IsSelection checks the current matched set of elements against a Selection object
|
||||
// and returns true if at least one of these elements matches.
|
||||
func (s *Selection) IsSelection(sel *Selection) bool {
|
||||
return s.FilterSelection(sel).Length() > 0
|
||||
}
|
||||
|
||||
// IsNodes checks the current matched set of elements against the specified nodes
|
||||
// and returns true if at least one of these elements matches.
|
||||
func (s *Selection) IsNodes(nodes ...*html.Node) bool {
|
||||
return s.FilterNodes(nodes...).Length() > 0
|
||||
}
|
||||
|
||||
// Contains returns true if the specified Node is within,
|
||||
// at any depth, one of the nodes in the Selection object.
|
||||
// It is NOT inclusive, to behave like jQuery's implementation, and
|
||||
// unlike Javascript's .contains, so if the contained
|
||||
// node is itself in the selection, it returns false.
|
||||
func (s *Selection) Contains(n *html.Node) bool {
|
||||
return sliceContains(s.Nodes, n)
|
||||
}
|
||||
|
|
@ -1,698 +0,0 @@
|
|||
package goquery
|
||||
|
||||
import "golang.org/x/net/html"
|
||||
|
||||
type siblingType int
|
||||
|
||||
// Sibling type, used internally when iterating over children at the same
|
||||
// level (siblings) to specify which nodes are requested.
|
||||
const (
|
||||
siblingPrevUntil siblingType = iota - 3
|
||||
siblingPrevAll
|
||||
siblingPrev
|
||||
siblingAll
|
||||
siblingNext
|
||||
siblingNextAll
|
||||
siblingNextUntil
|
||||
siblingAllIncludingNonElements
|
||||
)
|
||||
|
||||
// Find gets the descendants of each element in the current set of matched
|
||||
// elements, filtered by a selector. It returns a new Selection object
|
||||
// containing these matched elements.
|
||||
func (s *Selection) Find(selector string) *Selection {
|
||||
return pushStack(s, findWithMatcher(s.Nodes, compileMatcher(selector)))
|
||||
}
|
||||
|
||||
// FindMatcher gets the descendants of each element in the current set of matched
|
||||
// elements, filtered by the matcher. It returns a new Selection object
|
||||
// containing these matched elements.
|
||||
func (s *Selection) FindMatcher(m Matcher) *Selection {
|
||||
return pushStack(s, findWithMatcher(s.Nodes, m))
|
||||
}
|
||||
|
||||
// FindSelection gets the descendants of each element in the current
|
||||
// Selection, filtered by a Selection. It returns a new Selection object
|
||||
// containing these matched elements.
|
||||
func (s *Selection) FindSelection(sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return pushStack(s, nil)
|
||||
}
|
||||
return s.FindNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// FindNodes gets the descendants of each element in the current
|
||||
// Selection, filtered by some nodes. It returns a new Selection object
|
||||
// containing these matched elements.
|
||||
func (s *Selection) FindNodes(nodes ...*html.Node) *Selection {
|
||||
return pushStack(s, mapNodes(nodes, func(i int, n *html.Node) []*html.Node {
|
||||
if sliceContains(s.Nodes, n) {
|
||||
return []*html.Node{n}
|
||||
}
|
||||
return nil
|
||||
}))
|
||||
}
|
||||
|
||||
// Contents gets the children of each element in the Selection,
|
||||
// including text and comment nodes. It returns a new Selection object
|
||||
// containing these elements.
|
||||
func (s *Selection) Contents() *Selection {
|
||||
return pushStack(s, getChildrenNodes(s.Nodes, siblingAllIncludingNonElements))
|
||||
}
|
||||
|
||||
// ContentsFiltered gets the children of each element in the Selection,
|
||||
// filtered by the specified selector. It returns a new Selection
|
||||
// object containing these elements. Since selectors only act on Element nodes,
|
||||
// this function is an alias to ChildrenFiltered unless the selector is empty,
|
||||
// in which case it is an alias to Contents.
|
||||
func (s *Selection) ContentsFiltered(selector string) *Selection {
|
||||
if selector != "" {
|
||||
return s.ChildrenFiltered(selector)
|
||||
}
|
||||
return s.Contents()
|
||||
}
|
||||
|
||||
// ContentsMatcher gets the children of each element in the Selection,
|
||||
// filtered by the specified matcher. It returns a new Selection
|
||||
// object containing these elements. Since matchers only act on Element nodes,
|
||||
// this function is an alias to ChildrenMatcher.
|
||||
func (s *Selection) ContentsMatcher(m Matcher) *Selection {
|
||||
return s.ChildrenMatcher(m)
|
||||
}
|
||||
|
||||
// Children gets the child elements of each element in the Selection.
|
||||
// It returns a new Selection object containing these elements.
|
||||
func (s *Selection) Children() *Selection {
|
||||
return pushStack(s, getChildrenNodes(s.Nodes, siblingAll))
|
||||
}
|
||||
|
||||
// ChildrenFiltered gets the child elements of each element in the Selection,
|
||||
// filtered by the specified selector. It returns a new
|
||||
// Selection object containing these elements.
|
||||
func (s *Selection) ChildrenFiltered(selector string) *Selection {
|
||||
return filterAndPush(s, getChildrenNodes(s.Nodes, siblingAll), compileMatcher(selector))
|
||||
}
|
||||
|
||||
// ChildrenMatcher gets the child elements of each element in the Selection,
|
||||
// filtered by the specified matcher. It returns a new
|
||||
// Selection object containing these elements.
|
||||
func (s *Selection) ChildrenMatcher(m Matcher) *Selection {
|
||||
return filterAndPush(s, getChildrenNodes(s.Nodes, siblingAll), m)
|
||||
}
|
||||
|
||||
// Parent gets the parent of each element in the Selection. It returns a
|
||||
// new Selection object containing the matched elements.
|
||||
func (s *Selection) Parent() *Selection {
|
||||
return pushStack(s, getParentNodes(s.Nodes))
|
||||
}
|
||||
|
||||
// ParentFiltered gets the parent of each element in the Selection filtered by a
|
||||
// selector. It returns a new Selection object containing the matched elements.
|
||||
func (s *Selection) ParentFiltered(selector string) *Selection {
|
||||
return filterAndPush(s, getParentNodes(s.Nodes), compileMatcher(selector))
|
||||
}
|
||||
|
||||
// ParentMatcher gets the parent of each element in the Selection filtered by a
|
||||
// matcher. It returns a new Selection object containing the matched elements.
|
||||
func (s *Selection) ParentMatcher(m Matcher) *Selection {
|
||||
return filterAndPush(s, getParentNodes(s.Nodes), m)
|
||||
}
|
||||
|
||||
// Closest gets the first element that matches the selector by testing the
|
||||
// element itself and traversing up through its ancestors in the DOM tree.
|
||||
func (s *Selection) Closest(selector string) *Selection {
|
||||
cs := compileMatcher(selector)
|
||||
return s.ClosestMatcher(cs)
|
||||
}
|
||||
|
||||
// ClosestMatcher gets the first element that matches the matcher by testing the
|
||||
// element itself and traversing up through its ancestors in the DOM tree.
|
||||
func (s *Selection) ClosestMatcher(m Matcher) *Selection {
|
||||
return pushStack(s, mapNodes(s.Nodes, func(i int, n *html.Node) []*html.Node {
|
||||
// For each node in the selection, test the node itself, then each parent
|
||||
// until a match is found.
|
||||
for ; n != nil; n = n.Parent {
|
||||
if m.Match(n) {
|
||||
return []*html.Node{n}
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}))
|
||||
}
|
||||
|
||||
// ClosestNodes gets the first element that matches one of the nodes by testing the
|
||||
// element itself and traversing up through its ancestors in the DOM tree.
|
||||
func (s *Selection) ClosestNodes(nodes ...*html.Node) *Selection {
|
||||
set := make(map[*html.Node]bool)
|
||||
for _, n := range nodes {
|
||||
set[n] = true
|
||||
}
|
||||
return pushStack(s, mapNodes(s.Nodes, func(i int, n *html.Node) []*html.Node {
|
||||
// For each node in the selection, test the node itself, then each parent
|
||||
// until a match is found.
|
||||
for ; n != nil; n = n.Parent {
|
||||
if set[n] {
|
||||
return []*html.Node{n}
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}))
|
||||
}
|
||||
|
||||
// ClosestSelection gets the first element that matches one of the nodes in the
|
||||
// Selection by testing the element itself and traversing up through its ancestors
|
||||
// in the DOM tree.
|
||||
func (s *Selection) ClosestSelection(sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return pushStack(s, nil)
|
||||
}
|
||||
return s.ClosestNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// Parents gets the ancestors of each element in the current Selection. It
|
||||
// returns a new Selection object with the matched elements.
|
||||
func (s *Selection) Parents() *Selection {
|
||||
return pushStack(s, getParentsNodes(s.Nodes, nil, nil))
|
||||
}
|
||||
|
||||
// ParentsFiltered gets the ancestors of each element in the current
|
||||
// Selection. It returns a new Selection object with the matched elements.
|
||||
func (s *Selection) ParentsFiltered(selector string) *Selection {
|
||||
return filterAndPush(s, getParentsNodes(s.Nodes, nil, nil), compileMatcher(selector))
|
||||
}
|
||||
|
||||
// ParentsMatcher gets the ancestors of each element in the current
|
||||
// Selection. It returns a new Selection object with the matched elements.
|
||||
func (s *Selection) ParentsMatcher(m Matcher) *Selection {
|
||||
return filterAndPush(s, getParentsNodes(s.Nodes, nil, nil), m)
|
||||
}
|
||||
|
||||
// ParentsUntil gets the ancestors of each element in the Selection, up to but
|
||||
// not including the element matched by the selector. It returns a new Selection
|
||||
// object containing the matched elements.
|
||||
func (s *Selection) ParentsUntil(selector string) *Selection {
|
||||
return pushStack(s, getParentsNodes(s.Nodes, compileMatcher(selector), nil))
|
||||
}
|
||||
|
||||
// ParentsUntilMatcher gets the ancestors of each element in the Selection, up to but
|
||||
// not including the element matched by the matcher. It returns a new Selection
|
||||
// object containing the matched elements.
|
||||
func (s *Selection) ParentsUntilMatcher(m Matcher) *Selection {
|
||||
return pushStack(s, getParentsNodes(s.Nodes, m, nil))
|
||||
}
|
||||
|
||||
// ParentsUntilSelection gets the ancestors of each element in the Selection,
|
||||
// up to but not including the elements in the specified Selection. It returns a
|
||||
// new Selection object containing the matched elements.
|
||||
func (s *Selection) ParentsUntilSelection(sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return s.Parents()
|
||||
}
|
||||
return s.ParentsUntilNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// ParentsUntilNodes gets the ancestors of each element in the Selection,
|
||||
// up to but not including the specified nodes. It returns a
|
||||
// new Selection object containing the matched elements.
|
||||
func (s *Selection) ParentsUntilNodes(nodes ...*html.Node) *Selection {
|
||||
return pushStack(s, getParentsNodes(s.Nodes, nil, nodes))
|
||||
}
|
||||
|
||||
// ParentsFilteredUntil is like ParentsUntil, with the option to filter the
|
||||
// results based on a selector string. It returns a new Selection
|
||||
// object containing the matched elements.
|
||||
func (s *Selection) ParentsFilteredUntil(filterSelector, untilSelector string) *Selection {
|
||||
return filterAndPush(s, getParentsNodes(s.Nodes, compileMatcher(untilSelector), nil), compileMatcher(filterSelector))
|
||||
}
|
||||
|
||||
// ParentsFilteredUntilMatcher is like ParentsUntilMatcher, with the option to filter the
|
||||
// results based on a matcher. It returns a new Selection object containing the matched elements.
|
||||
func (s *Selection) ParentsFilteredUntilMatcher(filter, until Matcher) *Selection {
|
||||
return filterAndPush(s, getParentsNodes(s.Nodes, until, nil), filter)
|
||||
}
|
||||
|
||||
// ParentsFilteredUntilSelection is like ParentsUntilSelection, with the
|
||||
// option to filter the results based on a selector string. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) ParentsFilteredUntilSelection(filterSelector string, sel *Selection) *Selection {
|
||||
return s.ParentsMatcherUntilSelection(compileMatcher(filterSelector), sel)
|
||||
}
|
||||
|
||||
// ParentsMatcherUntilSelection is like ParentsUntilSelection, with the
|
||||
// option to filter the results based on a matcher. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) ParentsMatcherUntilSelection(filter Matcher, sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return s.ParentsMatcher(filter)
|
||||
}
|
||||
return s.ParentsMatcherUntilNodes(filter, sel.Nodes...)
|
||||
}
|
||||
|
||||
// ParentsFilteredUntilNodes is like ParentsUntilNodes, with the
|
||||
// option to filter the results based on a selector string. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) ParentsFilteredUntilNodes(filterSelector string, nodes ...*html.Node) *Selection {
|
||||
return filterAndPush(s, getParentsNodes(s.Nodes, nil, nodes), compileMatcher(filterSelector))
|
||||
}
|
||||
|
||||
// ParentsMatcherUntilNodes is like ParentsUntilNodes, with the
|
||||
// option to filter the results based on a matcher. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) ParentsMatcherUntilNodes(filter Matcher, nodes ...*html.Node) *Selection {
|
||||
return filterAndPush(s, getParentsNodes(s.Nodes, nil, nodes), filter)
|
||||
}
|
||||
|
||||
// Siblings gets the siblings of each element in the Selection. It returns
|
||||
// a new Selection object containing the matched elements.
|
||||
func (s *Selection) Siblings() *Selection {
|
||||
return pushStack(s, getSiblingNodes(s.Nodes, siblingAll, nil, nil))
|
||||
}
|
||||
|
||||
// SiblingsFiltered gets the siblings of each element in the Selection
|
||||
// filtered by a selector. It returns a new Selection object containing the
|
||||
// matched elements.
|
||||
func (s *Selection) SiblingsFiltered(selector string) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingAll, nil, nil), compileMatcher(selector))
|
||||
}
|
||||
|
||||
// SiblingsMatcher gets the siblings of each element in the Selection
|
||||
// filtered by a matcher. It returns a new Selection object containing the
|
||||
// matched elements.
|
||||
func (s *Selection) SiblingsMatcher(m Matcher) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingAll, nil, nil), m)
|
||||
}
|
||||
|
||||
// Next gets the immediately following sibling of each element in the
|
||||
// Selection. It returns a new Selection object containing the matched elements.
|
||||
func (s *Selection) Next() *Selection {
|
||||
return pushStack(s, getSiblingNodes(s.Nodes, siblingNext, nil, nil))
|
||||
}
|
||||
|
||||
// NextFiltered gets the immediately following sibling of each element in the
|
||||
// Selection filtered by a selector. It returns a new Selection object
|
||||
// containing the matched elements.
|
||||
func (s *Selection) NextFiltered(selector string) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingNext, nil, nil), compileMatcher(selector))
|
||||
}
|
||||
|
||||
// NextMatcher gets the immediately following sibling of each element in the
|
||||
// Selection filtered by a matcher. It returns a new Selection object
|
||||
// containing the matched elements.
|
||||
func (s *Selection) NextMatcher(m Matcher) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingNext, nil, nil), m)
|
||||
}
|
||||
|
||||
// NextAll gets all the following siblings of each element in the
|
||||
// Selection. It returns a new Selection object containing the matched elements.
|
||||
func (s *Selection) NextAll() *Selection {
|
||||
return pushStack(s, getSiblingNodes(s.Nodes, siblingNextAll, nil, nil))
|
||||
}
|
||||
|
||||
// NextAllFiltered gets all the following siblings of each element in the
|
||||
// Selection filtered by a selector. It returns a new Selection object
|
||||
// containing the matched elements.
|
||||
func (s *Selection) NextAllFiltered(selector string) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingNextAll, nil, nil), compileMatcher(selector))
|
||||
}
|
||||
|
||||
// NextAllMatcher gets all the following siblings of each element in the
|
||||
// Selection filtered by a matcher. It returns a new Selection object
|
||||
// containing the matched elements.
|
||||
func (s *Selection) NextAllMatcher(m Matcher) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingNextAll, nil, nil), m)
|
||||
}
|
||||
|
||||
// Prev gets the immediately preceding sibling of each element in the
|
||||
// Selection. It returns a new Selection object containing the matched elements.
|
||||
func (s *Selection) Prev() *Selection {
|
||||
return pushStack(s, getSiblingNodes(s.Nodes, siblingPrev, nil, nil))
|
||||
}
|
||||
|
||||
// PrevFiltered gets the immediately preceding sibling of each element in the
|
||||
// Selection filtered by a selector. It returns a new Selection object
|
||||
// containing the matched elements.
|
||||
func (s *Selection) PrevFiltered(selector string) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingPrev, nil, nil), compileMatcher(selector))
|
||||
}
|
||||
|
||||
// PrevMatcher gets the immediately preceding sibling of each element in the
|
||||
// Selection filtered by a matcher. It returns a new Selection object
|
||||
// containing the matched elements.
|
||||
func (s *Selection) PrevMatcher(m Matcher) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingPrev, nil, nil), m)
|
||||
}
|
||||
|
||||
// PrevAll gets all the preceding siblings of each element in the
|
||||
// Selection. It returns a new Selection object containing the matched elements.
|
||||
func (s *Selection) PrevAll() *Selection {
|
||||
return pushStack(s, getSiblingNodes(s.Nodes, siblingPrevAll, nil, nil))
|
||||
}
|
||||
|
||||
// PrevAllFiltered gets all the preceding siblings of each element in the
|
||||
// Selection filtered by a selector. It returns a new Selection object
|
||||
// containing the matched elements.
|
||||
func (s *Selection) PrevAllFiltered(selector string) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingPrevAll, nil, nil), compileMatcher(selector))
|
||||
}
|
||||
|
||||
// PrevAllMatcher gets all the preceding siblings of each element in the
|
||||
// Selection filtered by a matcher. It returns a new Selection object
|
||||
// containing the matched elements.
|
||||
func (s *Selection) PrevAllMatcher(m Matcher) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingPrevAll, nil, nil), m)
|
||||
}
|
||||
|
||||
// NextUntil gets all following siblings of each element up to but not
|
||||
// including the element matched by the selector. It returns a new Selection
|
||||
// object containing the matched elements.
|
||||
func (s *Selection) NextUntil(selector string) *Selection {
|
||||
return pushStack(s, getSiblingNodes(s.Nodes, siblingNextUntil,
|
||||
compileMatcher(selector), nil))
|
||||
}
|
||||
|
||||
// NextUntilMatcher gets all following siblings of each element up to but not
|
||||
// including the element matched by the matcher. It returns a new Selection
|
||||
// object containing the matched elements.
|
||||
func (s *Selection) NextUntilMatcher(m Matcher) *Selection {
|
||||
return pushStack(s, getSiblingNodes(s.Nodes, siblingNextUntil,
|
||||
m, nil))
|
||||
}
|
||||
|
||||
// NextUntilSelection gets all following siblings of each element up to but not
|
||||
// including the element matched by the Selection. It returns a new Selection
|
||||
// object containing the matched elements.
|
||||
func (s *Selection) NextUntilSelection(sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return s.NextAll()
|
||||
}
|
||||
return s.NextUntilNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// NextUntilNodes gets all following siblings of each element up to but not
|
||||
// including the element matched by the nodes. It returns a new Selection
|
||||
// object containing the matched elements.
|
||||
func (s *Selection) NextUntilNodes(nodes ...*html.Node) *Selection {
|
||||
return pushStack(s, getSiblingNodes(s.Nodes, siblingNextUntil,
|
||||
nil, nodes))
|
||||
}
|
||||
|
||||
// PrevUntil gets all preceding siblings of each element up to but not
|
||||
// including the element matched by the selector. It returns a new Selection
|
||||
// object containing the matched elements.
|
||||
func (s *Selection) PrevUntil(selector string) *Selection {
|
||||
return pushStack(s, getSiblingNodes(s.Nodes, siblingPrevUntil,
|
||||
compileMatcher(selector), nil))
|
||||
}
|
||||
|
||||
// PrevUntilMatcher gets all preceding siblings of each element up to but not
|
||||
// including the element matched by the matcher. It returns a new Selection
|
||||
// object containing the matched elements.
|
||||
func (s *Selection) PrevUntilMatcher(m Matcher) *Selection {
|
||||
return pushStack(s, getSiblingNodes(s.Nodes, siblingPrevUntil,
|
||||
m, nil))
|
||||
}
|
||||
|
||||
// PrevUntilSelection gets all preceding siblings of each element up to but not
|
||||
// including the element matched by the Selection. It returns a new Selection
|
||||
// object containing the matched elements.
|
||||
func (s *Selection) PrevUntilSelection(sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return s.PrevAll()
|
||||
}
|
||||
return s.PrevUntilNodes(sel.Nodes...)
|
||||
}
|
||||
|
||||
// PrevUntilNodes gets all preceding siblings of each element up to but not
|
||||
// including the element matched by the nodes. It returns a new Selection
|
||||
// object containing the matched elements.
|
||||
func (s *Selection) PrevUntilNodes(nodes ...*html.Node) *Selection {
|
||||
return pushStack(s, getSiblingNodes(s.Nodes, siblingPrevUntil,
|
||||
nil, nodes))
|
||||
}
|
||||
|
||||
// NextFilteredUntil is like NextUntil, with the option to filter
|
||||
// the results based on a selector string.
|
||||
// It returns a new Selection object containing the matched elements.
|
||||
func (s *Selection) NextFilteredUntil(filterSelector, untilSelector string) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingNextUntil,
|
||||
compileMatcher(untilSelector), nil), compileMatcher(filterSelector))
|
||||
}
|
||||
|
||||
// NextFilteredUntilMatcher is like NextUntilMatcher, with the option to filter
|
||||
// the results based on a matcher.
|
||||
// It returns a new Selection object containing the matched elements.
|
||||
func (s *Selection) NextFilteredUntilMatcher(filter, until Matcher) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingNextUntil,
|
||||
until, nil), filter)
|
||||
}
|
||||
|
||||
// NextFilteredUntilSelection is like NextUntilSelection, with the
|
||||
// option to filter the results based on a selector string. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) NextFilteredUntilSelection(filterSelector string, sel *Selection) *Selection {
|
||||
return s.NextMatcherUntilSelection(compileMatcher(filterSelector), sel)
|
||||
}
|
||||
|
||||
// NextMatcherUntilSelection is like NextUntilSelection, with the
|
||||
// option to filter the results based on a matcher. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) NextMatcherUntilSelection(filter Matcher, sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return s.NextMatcher(filter)
|
||||
}
|
||||
return s.NextMatcherUntilNodes(filter, sel.Nodes...)
|
||||
}
|
||||
|
||||
// NextFilteredUntilNodes is like NextUntilNodes, with the
|
||||
// option to filter the results based on a selector string. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) NextFilteredUntilNodes(filterSelector string, nodes ...*html.Node) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingNextUntil,
|
||||
nil, nodes), compileMatcher(filterSelector))
|
||||
}
|
||||
|
||||
// NextMatcherUntilNodes is like NextUntilNodes, with the
|
||||
// option to filter the results based on a matcher. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) NextMatcherUntilNodes(filter Matcher, nodes ...*html.Node) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingNextUntil,
|
||||
nil, nodes), filter)
|
||||
}
|
||||
|
||||
// PrevFilteredUntil is like PrevUntil, with the option to filter
|
||||
// the results based on a selector string.
|
||||
// It returns a new Selection object containing the matched elements.
|
||||
func (s *Selection) PrevFilteredUntil(filterSelector, untilSelector string) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingPrevUntil,
|
||||
compileMatcher(untilSelector), nil), compileMatcher(filterSelector))
|
||||
}
|
||||
|
||||
// PrevFilteredUntilMatcher is like PrevUntilMatcher, with the option to filter
|
||||
// the results based on a matcher.
|
||||
// It returns a new Selection object containing the matched elements.
|
||||
func (s *Selection) PrevFilteredUntilMatcher(filter, until Matcher) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingPrevUntil,
|
||||
until, nil), filter)
|
||||
}
|
||||
|
||||
// PrevFilteredUntilSelection is like PrevUntilSelection, with the
|
||||
// option to filter the results based on a selector string. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) PrevFilteredUntilSelection(filterSelector string, sel *Selection) *Selection {
|
||||
return s.PrevMatcherUntilSelection(compileMatcher(filterSelector), sel)
|
||||
}
|
||||
|
||||
// PrevMatcherUntilSelection is like PrevUntilSelection, with the
|
||||
// option to filter the results based on a matcher. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) PrevMatcherUntilSelection(filter Matcher, sel *Selection) *Selection {
|
||||
if sel == nil {
|
||||
return s.PrevMatcher(filter)
|
||||
}
|
||||
return s.PrevMatcherUntilNodes(filter, sel.Nodes...)
|
||||
}
|
||||
|
||||
// PrevFilteredUntilNodes is like PrevUntilNodes, with the
|
||||
// option to filter the results based on a selector string. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) PrevFilteredUntilNodes(filterSelector string, nodes ...*html.Node) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingPrevUntil,
|
||||
nil, nodes), compileMatcher(filterSelector))
|
||||
}
|
||||
|
||||
// PrevMatcherUntilNodes is like PrevUntilNodes, with the
|
||||
// option to filter the results based on a matcher. It returns a new
|
||||
// Selection object containing the matched elements.
|
||||
func (s *Selection) PrevMatcherUntilNodes(filter Matcher, nodes ...*html.Node) *Selection {
|
||||
return filterAndPush(s, getSiblingNodes(s.Nodes, siblingPrevUntil,
|
||||
nil, nodes), filter)
|
||||
}
|
||||
|
||||
// Filter and push filters the nodes based on a matcher, and pushes the results
|
||||
// on the stack, with the srcSel as previous selection.
|
||||
func filterAndPush(srcSel *Selection, nodes []*html.Node, m Matcher) *Selection {
|
||||
// Create a temporary Selection with the specified nodes to filter using winnow
|
||||
sel := &Selection{nodes, srcSel.document, nil}
|
||||
// Filter based on matcher and push on stack
|
||||
return pushStack(srcSel, winnow(sel, m, true))
|
||||
}
|
||||
|
||||
// Internal implementation of Find that return raw nodes.
|
||||
func findWithMatcher(nodes []*html.Node, m Matcher) []*html.Node {
|
||||
// Map nodes to find the matches within the children of each node
|
||||
return mapNodes(nodes, func(i int, n *html.Node) (result []*html.Node) {
|
||||
// Go down one level, becausejQuery's Find selects only within descendants
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
if c.Type == html.ElementNode {
|
||||
result = append(result, m.MatchAll(c)...)
|
||||
}
|
||||
}
|
||||
return
|
||||
})
|
||||
}
|
||||
|
||||
// Internal implementation to get all parent nodes, stopping at the specified
|
||||
// node (or nil if no stop).
|
||||
func getParentsNodes(nodes []*html.Node, stopm Matcher, stopNodes []*html.Node) []*html.Node {
|
||||
return mapNodes(nodes, func(i int, n *html.Node) (result []*html.Node) {
|
||||
for p := n.Parent; p != nil; p = p.Parent {
|
||||
sel := newSingleSelection(p, nil)
|
||||
if stopm != nil {
|
||||
if sel.IsMatcher(stopm) {
|
||||
break
|
||||
}
|
||||
} else if len(stopNodes) > 0 {
|
||||
if sel.IsNodes(stopNodes...) {
|
||||
break
|
||||
}
|
||||
}
|
||||
if p.Type == html.ElementNode {
|
||||
result = append(result, p)
|
||||
}
|
||||
}
|
||||
return
|
||||
})
|
||||
}
|
||||
|
||||
// Internal implementation of sibling nodes that return a raw slice of matches.
|
||||
func getSiblingNodes(nodes []*html.Node, st siblingType, untilm Matcher, untilNodes []*html.Node) []*html.Node {
|
||||
var f func(*html.Node) bool
|
||||
|
||||
// If the requested siblings are ...Until, create the test function to
|
||||
// determine if the until condition is reached (returns true if it is)
|
||||
if st == siblingNextUntil || st == siblingPrevUntil {
|
||||
f = func(n *html.Node) bool {
|
||||
if untilm != nil {
|
||||
// Matcher-based condition
|
||||
sel := newSingleSelection(n, nil)
|
||||
return sel.IsMatcher(untilm)
|
||||
} else if len(untilNodes) > 0 {
|
||||
// Nodes-based condition
|
||||
sel := newSingleSelection(n, nil)
|
||||
return sel.IsNodes(untilNodes...)
|
||||
}
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
return mapNodes(nodes, func(i int, n *html.Node) []*html.Node {
|
||||
return getChildrenWithSiblingType(n.Parent, st, n, f)
|
||||
})
|
||||
}
|
||||
|
||||
// Gets the children nodes of each node in the specified slice of nodes,
|
||||
// based on the sibling type request.
|
||||
func getChildrenNodes(nodes []*html.Node, st siblingType) []*html.Node {
|
||||
return mapNodes(nodes, func(i int, n *html.Node) []*html.Node {
|
||||
return getChildrenWithSiblingType(n, st, nil, nil)
|
||||
})
|
||||
}
|
||||
|
||||
// Gets the children of the specified parent, based on the requested sibling
|
||||
// type, skipping a specified node if required.
|
||||
func getChildrenWithSiblingType(parent *html.Node, st siblingType, skipNode *html.Node,
|
||||
untilFunc func(*html.Node) bool) (result []*html.Node) {
|
||||
|
||||
// Create the iterator function
|
||||
var iter = func(cur *html.Node) (ret *html.Node) {
|
||||
// Based on the sibling type requested, iterate the right way
|
||||
for {
|
||||
switch st {
|
||||
case siblingAll, siblingAllIncludingNonElements:
|
||||
if cur == nil {
|
||||
// First iteration, start with first child of parent
|
||||
// Skip node if required
|
||||
if ret = parent.FirstChild; ret == skipNode && skipNode != nil {
|
||||
ret = skipNode.NextSibling
|
||||
}
|
||||
} else {
|
||||
// Skip node if required
|
||||
if ret = cur.NextSibling; ret == skipNode && skipNode != nil {
|
||||
ret = skipNode.NextSibling
|
||||
}
|
||||
}
|
||||
case siblingPrev, siblingPrevAll, siblingPrevUntil:
|
||||
if cur == nil {
|
||||
// Start with previous sibling of the skip node
|
||||
ret = skipNode.PrevSibling
|
||||
} else {
|
||||
ret = cur.PrevSibling
|
||||
}
|
||||
case siblingNext, siblingNextAll, siblingNextUntil:
|
||||
if cur == nil {
|
||||
// Start with next sibling of the skip node
|
||||
ret = skipNode.NextSibling
|
||||
} else {
|
||||
ret = cur.NextSibling
|
||||
}
|
||||
default:
|
||||
panic("Invalid sibling type.")
|
||||
}
|
||||
if ret == nil || ret.Type == html.ElementNode || st == siblingAllIncludingNonElements {
|
||||
return
|
||||
}
|
||||
// Not a valid node, try again from this one
|
||||
cur = ret
|
||||
}
|
||||
}
|
||||
|
||||
for c := iter(nil); c != nil; c = iter(c) {
|
||||
// If this is an ...Until case, test before append (returns true
|
||||
// if the until condition is reached)
|
||||
if st == siblingNextUntil || st == siblingPrevUntil {
|
||||
if untilFunc(c) {
|
||||
return
|
||||
}
|
||||
}
|
||||
result = append(result, c)
|
||||
if st == siblingNext || st == siblingPrev {
|
||||
// Only one node was requested (immediate next or previous), so exit
|
||||
return
|
||||
}
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
// Internal implementation of parent nodes that return a raw slice of Nodes.
|
||||
func getParentNodes(nodes []*html.Node) []*html.Node {
|
||||
return mapNodes(nodes, func(i int, n *html.Node) []*html.Node {
|
||||
if n.Parent != nil && n.Parent.Type == html.ElementNode {
|
||||
return []*html.Node{n.Parent}
|
||||
}
|
||||
return nil
|
||||
})
|
||||
}
|
||||
|
||||
// Internal map function used by many traversing methods. Takes the source nodes
|
||||
// to iterate on and the mapping function that returns an array of nodes.
|
||||
// Returns an array of nodes mapped by calling the callback function once for
|
||||
// each node in the source nodes.
|
||||
func mapNodes(nodes []*html.Node, f func(int, *html.Node) []*html.Node) (result []*html.Node) {
|
||||
set := make(map[*html.Node]bool)
|
||||
for i, n := range nodes {
|
||||
if vals := f(i, n); len(vals) > 0 {
|
||||
result = appendWithoutDuplicates(result, vals, set)
|
||||
}
|
||||
}
|
||||
return result
|
||||
}
|
||||
|
|
@ -1,141 +0,0 @@
|
|||
package goquery
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"io"
|
||||
"net/http"
|
||||
"net/url"
|
||||
|
||||
"github.com/andybalholm/cascadia"
|
||||
|
||||
"golang.org/x/net/html"
|
||||
)
|
||||
|
||||
// Document represents an HTML document to be manipulated. Unlike jQuery, which
|
||||
// is loaded as part of a DOM document, and thus acts upon its containing
|
||||
// document, GoQuery doesn't know which HTML document to act upon. So it needs
|
||||
// to be told, and that's what the Document class is for. It holds the root
|
||||
// document node to manipulate, and can make selections on this document.
|
||||
type Document struct {
|
||||
*Selection
|
||||
Url *url.URL
|
||||
rootNode *html.Node
|
||||
}
|
||||
|
||||
// NewDocumentFromNode is a Document constructor that takes a root html Node
|
||||
// as argument.
|
||||
func NewDocumentFromNode(root *html.Node) *Document {
|
||||
return newDocument(root, nil)
|
||||
}
|
||||
|
||||
// NewDocument is a Document constructor that takes a string URL as argument.
|
||||
// It loads the specified document, parses it, and stores the root Document
|
||||
// node, ready to be manipulated.
|
||||
//
|
||||
// Deprecated: Use the net/http standard library package to make the request
|
||||
// and validate the response before calling goquery.NewDocumentFromReader
|
||||
// with the response's body.
|
||||
func NewDocument(url string) (*Document, error) {
|
||||
// Load the URL
|
||||
res, e := http.Get(url)
|
||||
if e != nil {
|
||||
return nil, e
|
||||
}
|
||||
return NewDocumentFromResponse(res)
|
||||
}
|
||||
|
||||
// NewDocumentFromReader returns a Document from an io.Reader.
|
||||
// It returns an error as second value if the reader's data cannot be parsed
|
||||
// as html. It does not check if the reader is also an io.Closer, the
|
||||
// provided reader is never closed by this call. It is the responsibility
|
||||
// of the caller to close it if required.
|
||||
func NewDocumentFromReader(r io.Reader) (*Document, error) {
|
||||
root, e := html.Parse(r)
|
||||
if e != nil {
|
||||
return nil, e
|
||||
}
|
||||
return newDocument(root, nil), nil
|
||||
}
|
||||
|
||||
// NewDocumentFromResponse is another Document constructor that takes an http response as argument.
|
||||
// It loads the specified response's document, parses it, and stores the root Document
|
||||
// node, ready to be manipulated. The response's body is closed on return.
|
||||
//
|
||||
// Deprecated: Use goquery.NewDocumentFromReader with the response's body.
|
||||
func NewDocumentFromResponse(res *http.Response) (*Document, error) {
|
||||
if res == nil {
|
||||
return nil, errors.New("Response is nil")
|
||||
}
|
||||
defer res.Body.Close()
|
||||
if res.Request == nil {
|
||||
return nil, errors.New("Response.Request is nil")
|
||||
}
|
||||
|
||||
// Parse the HTML into nodes
|
||||
root, e := html.Parse(res.Body)
|
||||
if e != nil {
|
||||
return nil, e
|
||||
}
|
||||
|
||||
// Create and fill the document
|
||||
return newDocument(root, res.Request.URL), nil
|
||||
}
|
||||
|
||||
// CloneDocument creates a deep-clone of a document.
|
||||
func CloneDocument(doc *Document) *Document {
|
||||
return newDocument(cloneNode(doc.rootNode), doc.Url)
|
||||
}
|
||||
|
||||
// Private constructor, make sure all fields are correctly filled.
|
||||
func newDocument(root *html.Node, url *url.URL) *Document {
|
||||
// Create and fill the document
|
||||
d := &Document{nil, url, root}
|
||||
d.Selection = newSingleSelection(root, d)
|
||||
return d
|
||||
}
|
||||
|
||||
// Selection represents a collection of nodes matching some criteria. The
|
||||
// initial Selection can be created by using Document.Find, and then
|
||||
// manipulated using the jQuery-like chainable syntax and methods.
|
||||
type Selection struct {
|
||||
Nodes []*html.Node
|
||||
document *Document
|
||||
prevSel *Selection
|
||||
}
|
||||
|
||||
// Helper constructor to create an empty selection
|
||||
func newEmptySelection(doc *Document) *Selection {
|
||||
return &Selection{nil, doc, nil}
|
||||
}
|
||||
|
||||
// Helper constructor to create a selection of only one node
|
||||
func newSingleSelection(node *html.Node, doc *Document) *Selection {
|
||||
return &Selection{[]*html.Node{node}, doc, nil}
|
||||
}
|
||||
|
||||
// Matcher is an interface that defines the methods to match
|
||||
// HTML nodes against a compiled selector string. Cascadia's
|
||||
// Selector implements this interface.
|
||||
type Matcher interface {
|
||||
Match(*html.Node) bool
|
||||
MatchAll(*html.Node) []*html.Node
|
||||
Filter([]*html.Node) []*html.Node
|
||||
}
|
||||
|
||||
// compileMatcher compiles the selector string s and returns
|
||||
// the corresponding Matcher. If s is an invalid selector string,
|
||||
// it returns a Matcher that fails all matches.
|
||||
func compileMatcher(s string) Matcher {
|
||||
cs, err := cascadia.Compile(s)
|
||||
if err != nil {
|
||||
return invalidMatcher{}
|
||||
}
|
||||
return cs
|
||||
}
|
||||
|
||||
// invalidMatcher is a Matcher that always fails to match.
|
||||
type invalidMatcher struct{}
|
||||
|
||||
func (invalidMatcher) Match(n *html.Node) bool { return false }
|
||||
func (invalidMatcher) MatchAll(n *html.Node) []*html.Node { return nil }
|
||||
func (invalidMatcher) Filter(ns []*html.Node) []*html.Node { return nil }
|
||||
|
|
@ -1,161 +0,0 @@
|
|||
package goquery
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
|
||||
"golang.org/x/net/html"
|
||||
)
|
||||
|
||||
// used to determine if a set (map[*html.Node]bool) should be used
|
||||
// instead of iterating over a slice. The set uses more memory and
|
||||
// is slower than slice iteration for small N.
|
||||
const minNodesForSet = 1000
|
||||
|
||||
var nodeNames = []string{
|
||||
html.ErrorNode: "#error",
|
||||
html.TextNode: "#text",
|
||||
html.DocumentNode: "#document",
|
||||
html.CommentNode: "#comment",
|
||||
}
|
||||
|
||||
// NodeName returns the node name of the first element in the selection.
|
||||
// It tries to behave in a similar way as the DOM's nodeName property
|
||||
// (https://developer.mozilla.org/en-US/docs/Web/API/Node/nodeName).
|
||||
//
|
||||
// Go's net/html package defines the following node types, listed with
|
||||
// the corresponding returned value from this function:
|
||||
//
|
||||
// ErrorNode : #error
|
||||
// TextNode : #text
|
||||
// DocumentNode : #document
|
||||
// ElementNode : the element's tag name
|
||||
// CommentNode : #comment
|
||||
// DoctypeNode : the name of the document type
|
||||
//
|
||||
func NodeName(s *Selection) string {
|
||||
if s.Length() == 0 {
|
||||
return ""
|
||||
}
|
||||
switch n := s.Get(0); n.Type {
|
||||
case html.ElementNode, html.DoctypeNode:
|
||||
return n.Data
|
||||
default:
|
||||
if n.Type >= 0 && int(n.Type) < len(nodeNames) {
|
||||
return nodeNames[n.Type]
|
||||
}
|
||||
return ""
|
||||
}
|
||||
}
|
||||
|
||||
// OuterHtml returns the outer HTML rendering of the first item in
|
||||
// the selection - that is, the HTML including the first element's
|
||||
// tag and attributes.
|
||||
//
|
||||
// Unlike InnerHtml, this is a function and not a method on the Selection,
|
||||
// because this is not a jQuery method (in javascript-land, this is
|
||||
// a property provided by the DOM).
|
||||
func OuterHtml(s *Selection) (string, error) {
|
||||
var buf bytes.Buffer
|
||||
|
||||
if s.Length() == 0 {
|
||||
return "", nil
|
||||
}
|
||||
n := s.Get(0)
|
||||
if err := html.Render(&buf, n); err != nil {
|
||||
return "", err
|
||||
}
|
||||
return buf.String(), nil
|
||||
}
|
||||
|
||||
// Loop through all container nodes to search for the target node.
|
||||
func sliceContains(container []*html.Node, contained *html.Node) bool {
|
||||
for _, n := range container {
|
||||
if nodeContains(n, contained) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// Checks if the contained node is within the container node.
|
||||
func nodeContains(container *html.Node, contained *html.Node) bool {
|
||||
// Check if the parent of the contained node is the container node, traversing
|
||||
// upward until the top is reached, or the container is found.
|
||||
for contained = contained.Parent; contained != nil; contained = contained.Parent {
|
||||
if container == contained {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// Checks if the target node is in the slice of nodes.
|
||||
func isInSlice(slice []*html.Node, node *html.Node) bool {
|
||||
return indexInSlice(slice, node) > -1
|
||||
}
|
||||
|
||||
// Returns the index of the target node in the slice, or -1.
|
||||
func indexInSlice(slice []*html.Node, node *html.Node) int {
|
||||
if node != nil {
|
||||
for i, n := range slice {
|
||||
if n == node {
|
||||
return i
|
||||
}
|
||||
}
|
||||
}
|
||||
return -1
|
||||
}
|
||||
|
||||
// Appends the new nodes to the target slice, making sure no duplicate is added.
|
||||
// There is no check to the original state of the target slice, so it may still
|
||||
// contain duplicates. The target slice is returned because append() may create
|
||||
// a new underlying array. If targetSet is nil, a local set is created with the
|
||||
// target if len(target) + len(nodes) is greater than minNodesForSet.
|
||||
func appendWithoutDuplicates(target []*html.Node, nodes []*html.Node, targetSet map[*html.Node]bool) []*html.Node {
|
||||
// if there are not that many nodes, don't use the map, faster to just use nested loops
|
||||
// (unless a non-nil targetSet is passed, in which case the caller knows better).
|
||||
if targetSet == nil && len(target)+len(nodes) < minNodesForSet {
|
||||
for _, n := range nodes {
|
||||
if !isInSlice(target, n) {
|
||||
target = append(target, n)
|
||||
}
|
||||
}
|
||||
return target
|
||||
}
|
||||
|
||||
// if a targetSet is passed, then assume it is reliable, otherwise create one
|
||||
// and initialize it with the current target contents.
|
||||
if targetSet == nil {
|
||||
targetSet = make(map[*html.Node]bool, len(target))
|
||||
for _, n := range target {
|
||||
targetSet[n] = true
|
||||
}
|
||||
}
|
||||
for _, n := range nodes {
|
||||
if !targetSet[n] {
|
||||
target = append(target, n)
|
||||
targetSet[n] = true
|
||||
}
|
||||
}
|
||||
|
||||
return target
|
||||
}
|
||||
|
||||
// Loop through a selection, returning only those nodes that pass the predicate
|
||||
// function.
|
||||
func grep(sel *Selection, predicate func(i int, s *Selection) bool) (result []*html.Node) {
|
||||
for i, n := range sel.Nodes {
|
||||
if predicate(i, newSingleSelection(n, sel.document)) {
|
||||
result = append(result, n)
|
||||
}
|
||||
}
|
||||
return result
|
||||
}
|
||||
|
||||
// Creates a new Selection object based on the specified nodes, and keeps the
|
||||
// source Selection object on the stack (linked list).
|
||||
func pushStack(fromSel *Selection, nodes []*html.Node) *Selection {
|
||||
result := &Selection{nodes, fromSel.document, fromSel}
|
||||
return result
|
||||
}
|
||||
|
|
@ -1,14 +0,0 @@
|
|||
language: go
|
||||
|
||||
go:
|
||||
- 1.3
|
||||
- 1.4
|
||||
|
||||
install:
|
||||
- go get github.com/andybalholm/cascadia
|
||||
|
||||
script:
|
||||
- go test -v
|
||||
|
||||
notifications:
|
||||
email: false
|
||||
|
|
@ -1,24 +0,0 @@
|
|||
Copyright (c) 2011 Andy Balholm. All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
# cascadia
|
||||
|
||||
[](https://travis-ci.org/andybalholm/cascadia)
|
||||
|
||||
The Cascadia package implements CSS selectors for use with the parse trees produced by the html package.
|
||||
|
||||
To test CSS selectors without writing Go code, check out [cascadia](https://github.com/suntong/cascadia) the command line tool, a thin wrapper around this package.
|
||||
|
|
@ -1,3 +0,0 @@
|
|||
module "github.com/andybalholm/cascadia"
|
||||
|
||||
require "golang.org/x/net" v0.0.0-20180218175443-cbe0f9307d01
|
||||
|
|
@ -1,835 +0,0 @@
|
|||
// Package cascadia is an implementation of CSS selectors.
|
||||
package cascadia
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"fmt"
|
||||
"regexp"
|
||||
"strconv"
|
||||
"strings"
|
||||
|
||||
"golang.org/x/net/html"
|
||||
)
|
||||
|
||||
// a parser for CSS selectors
|
||||
type parser struct {
|
||||
s string // the source text
|
||||
i int // the current position
|
||||
}
|
||||
|
||||
// parseEscape parses a backslash escape.
|
||||
func (p *parser) parseEscape() (result string, err error) {
|
||||
if len(p.s) < p.i+2 || p.s[p.i] != '\\' {
|
||||
return "", errors.New("invalid escape sequence")
|
||||
}
|
||||
|
||||
start := p.i + 1
|
||||
c := p.s[start]
|
||||
switch {
|
||||
case c == '\r' || c == '\n' || c == '\f':
|
||||
return "", errors.New("escaped line ending outside string")
|
||||
case hexDigit(c):
|
||||
// unicode escape (hex)
|
||||
var i int
|
||||
for i = start; i < p.i+6 && i < len(p.s) && hexDigit(p.s[i]); i++ {
|
||||
// empty
|
||||
}
|
||||
v, _ := strconv.ParseUint(p.s[start:i], 16, 21)
|
||||
if len(p.s) > i {
|
||||
switch p.s[i] {
|
||||
case '\r':
|
||||
i++
|
||||
if len(p.s) > i && p.s[i] == '\n' {
|
||||
i++
|
||||
}
|
||||
case ' ', '\t', '\n', '\f':
|
||||
i++
|
||||
}
|
||||
}
|
||||
p.i = i
|
||||
return string(rune(v)), nil
|
||||
}
|
||||
|
||||
// Return the literal character after the backslash.
|
||||
result = p.s[start : start+1]
|
||||
p.i += 2
|
||||
return result, nil
|
||||
}
|
||||
|
||||
func hexDigit(c byte) bool {
|
||||
return '0' <= c && c <= '9' || 'a' <= c && c <= 'f' || 'A' <= c && c <= 'F'
|
||||
}
|
||||
|
||||
// nameStart returns whether c can be the first character of an identifier
|
||||
// (not counting an initial hyphen, or an escape sequence).
|
||||
func nameStart(c byte) bool {
|
||||
return 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' || c == '_' || c > 127
|
||||
}
|
||||
|
||||
// nameChar returns whether c can be a character within an identifier
|
||||
// (not counting an escape sequence).
|
||||
func nameChar(c byte) bool {
|
||||
return 'a' <= c && c <= 'z' || 'A' <= c && c <= 'Z' || c == '_' || c > 127 ||
|
||||
c == '-' || '0' <= c && c <= '9'
|
||||
}
|
||||
|
||||
// parseIdentifier parses an identifier.
|
||||
func (p *parser) parseIdentifier() (result string, err error) {
|
||||
startingDash := false
|
||||
if len(p.s) > p.i && p.s[p.i] == '-' {
|
||||
startingDash = true
|
||||
p.i++
|
||||
}
|
||||
|
||||
if len(p.s) <= p.i {
|
||||
return "", errors.New("expected identifier, found EOF instead")
|
||||
}
|
||||
|
||||
if c := p.s[p.i]; !(nameStart(c) || c == '\\') {
|
||||
return "", fmt.Errorf("expected identifier, found %c instead", c)
|
||||
}
|
||||
|
||||
result, err = p.parseName()
|
||||
if startingDash && err == nil {
|
||||
result = "-" + result
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
// parseName parses a name (which is like an identifier, but doesn't have
|
||||
// extra restrictions on the first character).
|
||||
func (p *parser) parseName() (result string, err error) {
|
||||
i := p.i
|
||||
loop:
|
||||
for i < len(p.s) {
|
||||
c := p.s[i]
|
||||
switch {
|
||||
case nameChar(c):
|
||||
start := i
|
||||
for i < len(p.s) && nameChar(p.s[i]) {
|
||||
i++
|
||||
}
|
||||
result += p.s[start:i]
|
||||
case c == '\\':
|
||||
p.i = i
|
||||
val, err := p.parseEscape()
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
i = p.i
|
||||
result += val
|
||||
default:
|
||||
break loop
|
||||
}
|
||||
}
|
||||
|
||||
if result == "" {
|
||||
return "", errors.New("expected name, found EOF instead")
|
||||
}
|
||||
|
||||
p.i = i
|
||||
return result, nil
|
||||
}
|
||||
|
||||
// parseString parses a single- or double-quoted string.
|
||||
func (p *parser) parseString() (result string, err error) {
|
||||
i := p.i
|
||||
if len(p.s) < i+2 {
|
||||
return "", errors.New("expected string, found EOF instead")
|
||||
}
|
||||
|
||||
quote := p.s[i]
|
||||
i++
|
||||
|
||||
loop:
|
||||
for i < len(p.s) {
|
||||
switch p.s[i] {
|
||||
case '\\':
|
||||
if len(p.s) > i+1 {
|
||||
switch c := p.s[i+1]; c {
|
||||
case '\r':
|
||||
if len(p.s) > i+2 && p.s[i+2] == '\n' {
|
||||
i += 3
|
||||
continue loop
|
||||
}
|
||||
fallthrough
|
||||
case '\n', '\f':
|
||||
i += 2
|
||||
continue loop
|
||||
}
|
||||
}
|
||||
p.i = i
|
||||
val, err := p.parseEscape()
|
||||
if err != nil {
|
||||
return "", err
|
||||
}
|
||||
i = p.i
|
||||
result += val
|
||||
case quote:
|
||||
break loop
|
||||
case '\r', '\n', '\f':
|
||||
return "", errors.New("unexpected end of line in string")
|
||||
default:
|
||||
start := i
|
||||
for i < len(p.s) {
|
||||
if c := p.s[i]; c == quote || c == '\\' || c == '\r' || c == '\n' || c == '\f' {
|
||||
break
|
||||
}
|
||||
i++
|
||||
}
|
||||
result += p.s[start:i]
|
||||
}
|
||||
}
|
||||
|
||||
if i >= len(p.s) {
|
||||
return "", errors.New("EOF in string")
|
||||
}
|
||||
|
||||
// Consume the final quote.
|
||||
i++
|
||||
|
||||
p.i = i
|
||||
return result, nil
|
||||
}
|
||||
|
||||
// parseRegex parses a regular expression; the end is defined by encountering an
|
||||
// unmatched closing ')' or ']' which is not consumed
|
||||
func (p *parser) parseRegex() (rx *regexp.Regexp, err error) {
|
||||
i := p.i
|
||||
if len(p.s) < i+2 {
|
||||
return nil, errors.New("expected regular expression, found EOF instead")
|
||||
}
|
||||
|
||||
// number of open parens or brackets;
|
||||
// when it becomes negative, finished parsing regex
|
||||
open := 0
|
||||
|
||||
loop:
|
||||
for i < len(p.s) {
|
||||
switch p.s[i] {
|
||||
case '(', '[':
|
||||
open++
|
||||
case ')', ']':
|
||||
open--
|
||||
if open < 0 {
|
||||
break loop
|
||||
}
|
||||
}
|
||||
i++
|
||||
}
|
||||
|
||||
if i >= len(p.s) {
|
||||
return nil, errors.New("EOF in regular expression")
|
||||
}
|
||||
rx, err = regexp.Compile(p.s[p.i:i])
|
||||
p.i = i
|
||||
return rx, err
|
||||
}
|
||||
|
||||
// skipWhitespace consumes whitespace characters and comments.
|
||||
// It returns true if there was actually anything to skip.
|
||||
func (p *parser) skipWhitespace() bool {
|
||||
i := p.i
|
||||
for i < len(p.s) {
|
||||
switch p.s[i] {
|
||||
case ' ', '\t', '\r', '\n', '\f':
|
||||
i++
|
||||
continue
|
||||
case '/':
|
||||
if strings.HasPrefix(p.s[i:], "/*") {
|
||||
end := strings.Index(p.s[i+len("/*"):], "*/")
|
||||
if end != -1 {
|
||||
i += end + len("/**/")
|
||||
continue
|
||||
}
|
||||
}
|
||||
}
|
||||
break
|
||||
}
|
||||
|
||||
if i > p.i {
|
||||
p.i = i
|
||||
return true
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
|
||||
// consumeParenthesis consumes an opening parenthesis and any following
|
||||
// whitespace. It returns true if there was actually a parenthesis to skip.
|
||||
func (p *parser) consumeParenthesis() bool {
|
||||
if p.i < len(p.s) && p.s[p.i] == '(' {
|
||||
p.i++
|
||||
p.skipWhitespace()
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// consumeClosingParenthesis consumes a closing parenthesis and any preceding
|
||||
// whitespace. It returns true if there was actually a parenthesis to skip.
|
||||
func (p *parser) consumeClosingParenthesis() bool {
|
||||
i := p.i
|
||||
p.skipWhitespace()
|
||||
if p.i < len(p.s) && p.s[p.i] == ')' {
|
||||
p.i++
|
||||
return true
|
||||
}
|
||||
p.i = i
|
||||
return false
|
||||
}
|
||||
|
||||
// parseTypeSelector parses a type selector (one that matches by tag name).
|
||||
func (p *parser) parseTypeSelector() (result Selector, err error) {
|
||||
tag, err := p.parseIdentifier()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return typeSelector(tag), nil
|
||||
}
|
||||
|
||||
// parseIDSelector parses a selector that matches by id attribute.
|
||||
func (p *parser) parseIDSelector() (Selector, error) {
|
||||
if p.i >= len(p.s) {
|
||||
return nil, fmt.Errorf("expected id selector (#id), found EOF instead")
|
||||
}
|
||||
if p.s[p.i] != '#' {
|
||||
return nil, fmt.Errorf("expected id selector (#id), found '%c' instead", p.s[p.i])
|
||||
}
|
||||
|
||||
p.i++
|
||||
id, err := p.parseName()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return attributeEqualsSelector("id", id), nil
|
||||
}
|
||||
|
||||
// parseClassSelector parses a selector that matches by class attribute.
|
||||
func (p *parser) parseClassSelector() (Selector, error) {
|
||||
if p.i >= len(p.s) {
|
||||
return nil, fmt.Errorf("expected class selector (.class), found EOF instead")
|
||||
}
|
||||
if p.s[p.i] != '.' {
|
||||
return nil, fmt.Errorf("expected class selector (.class), found '%c' instead", p.s[p.i])
|
||||
}
|
||||
|
||||
p.i++
|
||||
class, err := p.parseIdentifier()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
return attributeIncludesSelector("class", class), nil
|
||||
}
|
||||
|
||||
// parseAttributeSelector parses a selector that matches by attribute value.
|
||||
func (p *parser) parseAttributeSelector() (Selector, error) {
|
||||
if p.i >= len(p.s) {
|
||||
return nil, fmt.Errorf("expected attribute selector ([attribute]), found EOF instead")
|
||||
}
|
||||
if p.s[p.i] != '[' {
|
||||
return nil, fmt.Errorf("expected attribute selector ([attribute]), found '%c' instead", p.s[p.i])
|
||||
}
|
||||
|
||||
p.i++
|
||||
p.skipWhitespace()
|
||||
key, err := p.parseIdentifier()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
p.skipWhitespace()
|
||||
if p.i >= len(p.s) {
|
||||
return nil, errors.New("unexpected EOF in attribute selector")
|
||||
}
|
||||
|
||||
if p.s[p.i] == ']' {
|
||||
p.i++
|
||||
return attributeExistsSelector(key), nil
|
||||
}
|
||||
|
||||
if p.i+2 >= len(p.s) {
|
||||
return nil, errors.New("unexpected EOF in attribute selector")
|
||||
}
|
||||
|
||||
op := p.s[p.i : p.i+2]
|
||||
if op[0] == '=' {
|
||||
op = "="
|
||||
} else if op[1] != '=' {
|
||||
return nil, fmt.Errorf(`expected equality operator, found "%s" instead`, op)
|
||||
}
|
||||
p.i += len(op)
|
||||
|
||||
p.skipWhitespace()
|
||||
if p.i >= len(p.s) {
|
||||
return nil, errors.New("unexpected EOF in attribute selector")
|
||||
}
|
||||
var val string
|
||||
var rx *regexp.Regexp
|
||||
if op == "#=" {
|
||||
rx, err = p.parseRegex()
|
||||
} else {
|
||||
switch p.s[p.i] {
|
||||
case '\'', '"':
|
||||
val, err = p.parseString()
|
||||
default:
|
||||
val, err = p.parseIdentifier()
|
||||
}
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
p.skipWhitespace()
|
||||
if p.i >= len(p.s) {
|
||||
return nil, errors.New("unexpected EOF in attribute selector")
|
||||
}
|
||||
if p.s[p.i] != ']' {
|
||||
return nil, fmt.Errorf("expected ']', found '%c' instead", p.s[p.i])
|
||||
}
|
||||
p.i++
|
||||
|
||||
switch op {
|
||||
case "=":
|
||||
return attributeEqualsSelector(key, val), nil
|
||||
case "!=":
|
||||
return attributeNotEqualSelector(key, val), nil
|
||||
case "~=":
|
||||
return attributeIncludesSelector(key, val), nil
|
||||
case "|=":
|
||||
return attributeDashmatchSelector(key, val), nil
|
||||
case "^=":
|
||||
return attributePrefixSelector(key, val), nil
|
||||
case "$=":
|
||||
return attributeSuffixSelector(key, val), nil
|
||||
case "*=":
|
||||
return attributeSubstringSelector(key, val), nil
|
||||
case "#=":
|
||||
return attributeRegexSelector(key, rx), nil
|
||||
}
|
||||
|
||||
return nil, fmt.Errorf("attribute operator %q is not supported", op)
|
||||
}
|
||||
|
||||
var errExpectedParenthesis = errors.New("expected '(' but didn't find it")
|
||||
var errExpectedClosingParenthesis = errors.New("expected ')' but didn't find it")
|
||||
var errUnmatchedParenthesis = errors.New("unmatched '('")
|
||||
|
||||
// parsePseudoclassSelector parses a pseudoclass selector like :not(p).
|
||||
func (p *parser) parsePseudoclassSelector() (Selector, error) {
|
||||
if p.i >= len(p.s) {
|
||||
return nil, fmt.Errorf("expected pseudoclass selector (:pseudoclass), found EOF instead")
|
||||
}
|
||||
if p.s[p.i] != ':' {
|
||||
return nil, fmt.Errorf("expected attribute selector (:pseudoclass), found '%c' instead", p.s[p.i])
|
||||
}
|
||||
|
||||
p.i++
|
||||
name, err := p.parseIdentifier()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
name = toLowerASCII(name)
|
||||
|
||||
switch name {
|
||||
case "not", "has", "haschild":
|
||||
if !p.consumeParenthesis() {
|
||||
return nil, errExpectedParenthesis
|
||||
}
|
||||
sel, parseErr := p.parseSelectorGroup()
|
||||
if parseErr != nil {
|
||||
return nil, parseErr
|
||||
}
|
||||
if !p.consumeClosingParenthesis() {
|
||||
return nil, errExpectedClosingParenthesis
|
||||
}
|
||||
|
||||
switch name {
|
||||
case "not":
|
||||
return negatedSelector(sel), nil
|
||||
case "has":
|
||||
return hasDescendantSelector(sel), nil
|
||||
case "haschild":
|
||||
return hasChildSelector(sel), nil
|
||||
}
|
||||
|
||||
case "contains", "containsown":
|
||||
if !p.consumeParenthesis() {
|
||||
return nil, errExpectedParenthesis
|
||||
}
|
||||
if p.i == len(p.s) {
|
||||
return nil, errUnmatchedParenthesis
|
||||
}
|
||||
var val string
|
||||
switch p.s[p.i] {
|
||||
case '\'', '"':
|
||||
val, err = p.parseString()
|
||||
default:
|
||||
val, err = p.parseIdentifier()
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
val = strings.ToLower(val)
|
||||
p.skipWhitespace()
|
||||
if p.i >= len(p.s) {
|
||||
return nil, errors.New("unexpected EOF in pseudo selector")
|
||||
}
|
||||
if !p.consumeClosingParenthesis() {
|
||||
return nil, errExpectedClosingParenthesis
|
||||
}
|
||||
|
||||
switch name {
|
||||
case "contains":
|
||||
return textSubstrSelector(val), nil
|
||||
case "containsown":
|
||||
return ownTextSubstrSelector(val), nil
|
||||
}
|
||||
|
||||
case "matches", "matchesown":
|
||||
if !p.consumeParenthesis() {
|
||||
return nil, errExpectedParenthesis
|
||||
}
|
||||
rx, err := p.parseRegex()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if p.i >= len(p.s) {
|
||||
return nil, errors.New("unexpected EOF in pseudo selector")
|
||||
}
|
||||
if !p.consumeClosingParenthesis() {
|
||||
return nil, errExpectedClosingParenthesis
|
||||
}
|
||||
|
||||
switch name {
|
||||
case "matches":
|
||||
return textRegexSelector(rx), nil
|
||||
case "matchesown":
|
||||
return ownTextRegexSelector(rx), nil
|
||||
}
|
||||
|
||||
case "nth-child", "nth-last-child", "nth-of-type", "nth-last-of-type":
|
||||
if !p.consumeParenthesis() {
|
||||
return nil, errExpectedParenthesis
|
||||
}
|
||||
a, b, err := p.parseNth()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if !p.consumeClosingParenthesis() {
|
||||
return nil, errExpectedClosingParenthesis
|
||||
}
|
||||
if a == 0 {
|
||||
switch name {
|
||||
case "nth-child":
|
||||
return simpleNthChildSelector(b, false), nil
|
||||
case "nth-of-type":
|
||||
return simpleNthChildSelector(b, true), nil
|
||||
case "nth-last-child":
|
||||
return simpleNthLastChildSelector(b, false), nil
|
||||
case "nth-last-of-type":
|
||||
return simpleNthLastChildSelector(b, true), nil
|
||||
}
|
||||
}
|
||||
return nthChildSelector(a, b,
|
||||
name == "nth-last-child" || name == "nth-last-of-type",
|
||||
name == "nth-of-type" || name == "nth-last-of-type"),
|
||||
nil
|
||||
|
||||
case "first-child":
|
||||
return simpleNthChildSelector(1, false), nil
|
||||
case "last-child":
|
||||
return simpleNthLastChildSelector(1, false), nil
|
||||
case "first-of-type":
|
||||
return simpleNthChildSelector(1, true), nil
|
||||
case "last-of-type":
|
||||
return simpleNthLastChildSelector(1, true), nil
|
||||
case "only-child":
|
||||
return onlyChildSelector(false), nil
|
||||
case "only-of-type":
|
||||
return onlyChildSelector(true), nil
|
||||
case "input":
|
||||
return inputSelector, nil
|
||||
case "empty":
|
||||
return emptyElementSelector, nil
|
||||
case "root":
|
||||
return rootSelector, nil
|
||||
}
|
||||
|
||||
return nil, fmt.Errorf("unknown pseudoclass :%s", name)
|
||||
}
|
||||
|
||||
// parseInteger parses a decimal integer.
|
||||
func (p *parser) parseInteger() (int, error) {
|
||||
i := p.i
|
||||
start := i
|
||||
for i < len(p.s) && '0' <= p.s[i] && p.s[i] <= '9' {
|
||||
i++
|
||||
}
|
||||
if i == start {
|
||||
return 0, errors.New("expected integer, but didn't find it")
|
||||
}
|
||||
p.i = i
|
||||
|
||||
val, err := strconv.Atoi(p.s[start:i])
|
||||
if err != nil {
|
||||
return 0, err
|
||||
}
|
||||
|
||||
return val, nil
|
||||
}
|
||||
|
||||
// parseNth parses the argument for :nth-child (normally of the form an+b).
|
||||
func (p *parser) parseNth() (a, b int, err error) {
|
||||
// initial state
|
||||
if p.i >= len(p.s) {
|
||||
goto eof
|
||||
}
|
||||
switch p.s[p.i] {
|
||||
case '-':
|
||||
p.i++
|
||||
goto negativeA
|
||||
case '+':
|
||||
p.i++
|
||||
goto positiveA
|
||||
case '0', '1', '2', '3', '4', '5', '6', '7', '8', '9':
|
||||
goto positiveA
|
||||
case 'n', 'N':
|
||||
a = 1
|
||||
p.i++
|
||||
goto readN
|
||||
case 'o', 'O', 'e', 'E':
|
||||
id, nameErr := p.parseName()
|
||||
if nameErr != nil {
|
||||
return 0, 0, nameErr
|
||||
}
|
||||
id = toLowerASCII(id)
|
||||
if id == "odd" {
|
||||
return 2, 1, nil
|
||||
}
|
||||
if id == "even" {
|
||||
return 2, 0, nil
|
||||
}
|
||||
return 0, 0, fmt.Errorf("expected 'odd' or 'even', but found '%s' instead", id)
|
||||
default:
|
||||
goto invalid
|
||||
}
|
||||
|
||||
positiveA:
|
||||
if p.i >= len(p.s) {
|
||||
goto eof
|
||||
}
|
||||
switch p.s[p.i] {
|
||||
case '0', '1', '2', '3', '4', '5', '6', '7', '8', '9':
|
||||
a, err = p.parseInteger()
|
||||
if err != nil {
|
||||
return 0, 0, err
|
||||
}
|
||||
goto readA
|
||||
case 'n', 'N':
|
||||
a = 1
|
||||
p.i++
|
||||
goto readN
|
||||
default:
|
||||
goto invalid
|
||||
}
|
||||
|
||||
negativeA:
|
||||
if p.i >= len(p.s) {
|
||||
goto eof
|
||||
}
|
||||
switch p.s[p.i] {
|
||||
case '0', '1', '2', '3', '4', '5', '6', '7', '8', '9':
|
||||
a, err = p.parseInteger()
|
||||
if err != nil {
|
||||
return 0, 0, err
|
||||
}
|
||||
a = -a
|
||||
goto readA
|
||||
case 'n', 'N':
|
||||
a = -1
|
||||
p.i++
|
||||
goto readN
|
||||
default:
|
||||
goto invalid
|
||||
}
|
||||
|
||||
readA:
|
||||
if p.i >= len(p.s) {
|
||||
goto eof
|
||||
}
|
||||
switch p.s[p.i] {
|
||||
case 'n', 'N':
|
||||
p.i++
|
||||
goto readN
|
||||
default:
|
||||
// The number we read as a is actually b.
|
||||
return 0, a, nil
|
||||
}
|
||||
|
||||
readN:
|
||||
p.skipWhitespace()
|
||||
if p.i >= len(p.s) {
|
||||
goto eof
|
||||
}
|
||||
switch p.s[p.i] {
|
||||
case '+':
|
||||
p.i++
|
||||
p.skipWhitespace()
|
||||
b, err = p.parseInteger()
|
||||
if err != nil {
|
||||
return 0, 0, err
|
||||
}
|
||||
return a, b, nil
|
||||
case '-':
|
||||
p.i++
|
||||
p.skipWhitespace()
|
||||
b, err = p.parseInteger()
|
||||
if err != nil {
|
||||
return 0, 0, err
|
||||
}
|
||||
return a, -b, nil
|
||||
default:
|
||||
return a, 0, nil
|
||||
}
|
||||
|
||||
eof:
|
||||
return 0, 0, errors.New("unexpected EOF while attempting to parse expression of form an+b")
|
||||
|
||||
invalid:
|
||||
return 0, 0, errors.New("unexpected character while attempting to parse expression of form an+b")
|
||||
}
|
||||
|
||||
// parseSimpleSelectorSequence parses a selector sequence that applies to
|
||||
// a single element.
|
||||
func (p *parser) parseSimpleSelectorSequence() (Selector, error) {
|
||||
var result Selector
|
||||
|
||||
if p.i >= len(p.s) {
|
||||
return nil, errors.New("expected selector, found EOF instead")
|
||||
}
|
||||
|
||||
switch p.s[p.i] {
|
||||
case '*':
|
||||
// It's the universal selector. Just skip over it, since it doesn't affect the meaning.
|
||||
p.i++
|
||||
case '#', '.', '[', ':':
|
||||
// There's no type selector. Wait to process the other till the main loop.
|
||||
default:
|
||||
r, err := p.parseTypeSelector()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
result = r
|
||||
}
|
||||
|
||||
loop:
|
||||
for p.i < len(p.s) {
|
||||
var ns Selector
|
||||
var err error
|
||||
switch p.s[p.i] {
|
||||
case '#':
|
||||
ns, err = p.parseIDSelector()
|
||||
case '.':
|
||||
ns, err = p.parseClassSelector()
|
||||
case '[':
|
||||
ns, err = p.parseAttributeSelector()
|
||||
case ':':
|
||||
ns, err = p.parsePseudoclassSelector()
|
||||
default:
|
||||
break loop
|
||||
}
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if result == nil {
|
||||
result = ns
|
||||
} else {
|
||||
result = intersectionSelector(result, ns)
|
||||
}
|
||||
}
|
||||
|
||||
if result == nil {
|
||||
result = func(n *html.Node) bool {
|
||||
return n.Type == html.ElementNode
|
||||
}
|
||||
}
|
||||
|
||||
return result, nil
|
||||
}
|
||||
|
||||
// parseSelector parses a selector that may include combinators.
|
||||
func (p *parser) parseSelector() (result Selector, err error) {
|
||||
p.skipWhitespace()
|
||||
result, err = p.parseSimpleSelectorSequence()
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
|
||||
for {
|
||||
var combinator byte
|
||||
if p.skipWhitespace() {
|
||||
combinator = ' '
|
||||
}
|
||||
if p.i >= len(p.s) {
|
||||
return
|
||||
}
|
||||
|
||||
switch p.s[p.i] {
|
||||
case '+', '>', '~':
|
||||
combinator = p.s[p.i]
|
||||
p.i++
|
||||
p.skipWhitespace()
|
||||
case ',', ')':
|
||||
// These characters can't begin a selector, but they can legally occur after one.
|
||||
return
|
||||
}
|
||||
|
||||
if combinator == 0 {
|
||||
return
|
||||
}
|
||||
|
||||
c, err := p.parseSimpleSelectorSequence()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
switch combinator {
|
||||
case ' ':
|
||||
result = descendantSelector(result, c)
|
||||
case '>':
|
||||
result = childSelector(result, c)
|
||||
case '+':
|
||||
result = siblingSelector(result, c, true)
|
||||
case '~':
|
||||
result = siblingSelector(result, c, false)
|
||||
}
|
||||
}
|
||||
|
||||
panic("unreachable")
|
||||
}
|
||||
|
||||
// parseSelectorGroup parses a group of selectors, separated by commas.
|
||||
func (p *parser) parseSelectorGroup() (result Selector, err error) {
|
||||
result, err = p.parseSelector()
|
||||
if err != nil {
|
||||
return
|
||||
}
|
||||
|
||||
for p.i < len(p.s) {
|
||||
if p.s[p.i] != ',' {
|
||||
return result, nil
|
||||
}
|
||||
p.i++
|
||||
c, err := p.parseSelector()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
result = unionSelector(result, c)
|
||||
}
|
||||
|
||||
return
|
||||
}
|
||||
|
|
@ -1,622 +0,0 @@
|
|||
package cascadia
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"regexp"
|
||||
"strings"
|
||||
|
||||
"golang.org/x/net/html"
|
||||
)
|
||||
|
||||
// the Selector type, and functions for creating them
|
||||
|
||||
// A Selector is a function which tells whether a node matches or not.
|
||||
type Selector func(*html.Node) bool
|
||||
|
||||
// hasChildMatch returns whether n has any child that matches a.
|
||||
func hasChildMatch(n *html.Node, a Selector) bool {
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
if a(c) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// hasDescendantMatch performs a depth-first search of n's descendants,
|
||||
// testing whether any of them match a. It returns true as soon as a match is
|
||||
// found, or false if no match is found.
|
||||
func hasDescendantMatch(n *html.Node, a Selector) bool {
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
if a(c) || (c.Type == html.ElementNode && hasDescendantMatch(c, a)) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// Compile parses a selector and returns, if successful, a Selector object
|
||||
// that can be used to match against html.Node objects.
|
||||
func Compile(sel string) (Selector, error) {
|
||||
p := &parser{s: sel}
|
||||
compiled, err := p.parseSelectorGroup()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
|
||||
if p.i < len(sel) {
|
||||
return nil, fmt.Errorf("parsing %q: %d bytes left over", sel, len(sel)-p.i)
|
||||
}
|
||||
|
||||
return compiled, nil
|
||||
}
|
||||
|
||||
// MustCompile is like Compile, but panics instead of returning an error.
|
||||
func MustCompile(sel string) Selector {
|
||||
compiled, err := Compile(sel)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
return compiled
|
||||
}
|
||||
|
||||
// MatchAll returns a slice of the nodes that match the selector,
|
||||
// from n and its children.
|
||||
func (s Selector) MatchAll(n *html.Node) []*html.Node {
|
||||
return s.matchAllInto(n, nil)
|
||||
}
|
||||
|
||||
func (s Selector) matchAllInto(n *html.Node, storage []*html.Node) []*html.Node {
|
||||
if s(n) {
|
||||
storage = append(storage, n)
|
||||
}
|
||||
|
||||
for child := n.FirstChild; child != nil; child = child.NextSibling {
|
||||
storage = s.matchAllInto(child, storage)
|
||||
}
|
||||
|
||||
return storage
|
||||
}
|
||||
|
||||
// Match returns true if the node matches the selector.
|
||||
func (s Selector) Match(n *html.Node) bool {
|
||||
return s(n)
|
||||
}
|
||||
|
||||
// MatchFirst returns the first node that matches s, from n and its children.
|
||||
func (s Selector) MatchFirst(n *html.Node) *html.Node {
|
||||
if s.Match(n) {
|
||||
return n
|
||||
}
|
||||
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
m := s.MatchFirst(c)
|
||||
if m != nil {
|
||||
return m
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Filter returns the nodes in nodes that match the selector.
|
||||
func (s Selector) Filter(nodes []*html.Node) (result []*html.Node) {
|
||||
for _, n := range nodes {
|
||||
if s(n) {
|
||||
result = append(result, n)
|
||||
}
|
||||
}
|
||||
return result
|
||||
}
|
||||
|
||||
// typeSelector returns a Selector that matches elements with a given tag name.
|
||||
func typeSelector(tag string) Selector {
|
||||
tag = toLowerASCII(tag)
|
||||
return func(n *html.Node) bool {
|
||||
return n.Type == html.ElementNode && n.Data == tag
|
||||
}
|
||||
}
|
||||
|
||||
// toLowerASCII returns s with all ASCII capital letters lowercased.
|
||||
func toLowerASCII(s string) string {
|
||||
var b []byte
|
||||
for i := 0; i < len(s); i++ {
|
||||
if c := s[i]; 'A' <= c && c <= 'Z' {
|
||||
if b == nil {
|
||||
b = make([]byte, len(s))
|
||||
copy(b, s)
|
||||
}
|
||||
b[i] = s[i] + ('a' - 'A')
|
||||
}
|
||||
}
|
||||
|
||||
if b == nil {
|
||||
return s
|
||||
}
|
||||
|
||||
return string(b)
|
||||
}
|
||||
|
||||
// attributeSelector returns a Selector that matches elements
|
||||
// where the attribute named key satisifes the function f.
|
||||
func attributeSelector(key string, f func(string) bool) Selector {
|
||||
key = toLowerASCII(key)
|
||||
return func(n *html.Node) bool {
|
||||
if n.Type != html.ElementNode {
|
||||
return false
|
||||
}
|
||||
for _, a := range n.Attr {
|
||||
if a.Key == key && f(a.Val) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
// attributeExistsSelector returns a Selector that matches elements that have
|
||||
// an attribute named key.
|
||||
func attributeExistsSelector(key string) Selector {
|
||||
return attributeSelector(key, func(string) bool { return true })
|
||||
}
|
||||
|
||||
// attributeEqualsSelector returns a Selector that matches elements where
|
||||
// the attribute named key has the value val.
|
||||
func attributeEqualsSelector(key, val string) Selector {
|
||||
return attributeSelector(key,
|
||||
func(s string) bool {
|
||||
return s == val
|
||||
})
|
||||
}
|
||||
|
||||
// attributeNotEqualSelector returns a Selector that matches elements where
|
||||
// the attribute named key does not have the value val.
|
||||
func attributeNotEqualSelector(key, val string) Selector {
|
||||
key = toLowerASCII(key)
|
||||
return func(n *html.Node) bool {
|
||||
if n.Type != html.ElementNode {
|
||||
return false
|
||||
}
|
||||
for _, a := range n.Attr {
|
||||
if a.Key == key && a.Val == val {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
// attributeIncludesSelector returns a Selector that matches elements where
|
||||
// the attribute named key is a whitespace-separated list that includes val.
|
||||
func attributeIncludesSelector(key, val string) Selector {
|
||||
return attributeSelector(key,
|
||||
func(s string) bool {
|
||||
for s != "" {
|
||||
i := strings.IndexAny(s, " \t\r\n\f")
|
||||
if i == -1 {
|
||||
return s == val
|
||||
}
|
||||
if s[:i] == val {
|
||||
return true
|
||||
}
|
||||
s = s[i+1:]
|
||||
}
|
||||
return false
|
||||
})
|
||||
}
|
||||
|
||||
// attributeDashmatchSelector returns a Selector that matches elements where
|
||||
// the attribute named key equals val or starts with val plus a hyphen.
|
||||
func attributeDashmatchSelector(key, val string) Selector {
|
||||
return attributeSelector(key,
|
||||
func(s string) bool {
|
||||
if s == val {
|
||||
return true
|
||||
}
|
||||
if len(s) <= len(val) {
|
||||
return false
|
||||
}
|
||||
if s[:len(val)] == val && s[len(val)] == '-' {
|
||||
return true
|
||||
}
|
||||
return false
|
||||
})
|
||||
}
|
||||
|
||||
// attributePrefixSelector returns a Selector that matches elements where
|
||||
// the attribute named key starts with val.
|
||||
func attributePrefixSelector(key, val string) Selector {
|
||||
return attributeSelector(key,
|
||||
func(s string) bool {
|
||||
if strings.TrimSpace(s) == "" {
|
||||
return false
|
||||
}
|
||||
return strings.HasPrefix(s, val)
|
||||
})
|
||||
}
|
||||
|
||||
// attributeSuffixSelector returns a Selector that matches elements where
|
||||
// the attribute named key ends with val.
|
||||
func attributeSuffixSelector(key, val string) Selector {
|
||||
return attributeSelector(key,
|
||||
func(s string) bool {
|
||||
if strings.TrimSpace(s) == "" {
|
||||
return false
|
||||
}
|
||||
return strings.HasSuffix(s, val)
|
||||
})
|
||||
}
|
||||
|
||||
// attributeSubstringSelector returns a Selector that matches nodes where
|
||||
// the attribute named key contains val.
|
||||
func attributeSubstringSelector(key, val string) Selector {
|
||||
return attributeSelector(key,
|
||||
func(s string) bool {
|
||||
if strings.TrimSpace(s) == "" {
|
||||
return false
|
||||
}
|
||||
return strings.Contains(s, val)
|
||||
})
|
||||
}
|
||||
|
||||
// attributeRegexSelector returns a Selector that matches nodes where
|
||||
// the attribute named key matches the regular expression rx
|
||||
func attributeRegexSelector(key string, rx *regexp.Regexp) Selector {
|
||||
return attributeSelector(key,
|
||||
func(s string) bool {
|
||||
return rx.MatchString(s)
|
||||
})
|
||||
}
|
||||
|
||||
// intersectionSelector returns a selector that matches nodes that match
|
||||
// both a and b.
|
||||
func intersectionSelector(a, b Selector) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
return a(n) && b(n)
|
||||
}
|
||||
}
|
||||
|
||||
// unionSelector returns a selector that matches elements that match
|
||||
// either a or b.
|
||||
func unionSelector(a, b Selector) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
return a(n) || b(n)
|
||||
}
|
||||
}
|
||||
|
||||
// negatedSelector returns a selector that matches elements that do not match a.
|
||||
func negatedSelector(a Selector) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
if n.Type != html.ElementNode {
|
||||
return false
|
||||
}
|
||||
return !a(n)
|
||||
}
|
||||
}
|
||||
|
||||
// writeNodeText writes the text contained in n and its descendants to b.
|
||||
func writeNodeText(n *html.Node, b *bytes.Buffer) {
|
||||
switch n.Type {
|
||||
case html.TextNode:
|
||||
b.WriteString(n.Data)
|
||||
case html.ElementNode:
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
writeNodeText(c, b)
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// nodeText returns the text contained in n and its descendants.
|
||||
func nodeText(n *html.Node) string {
|
||||
var b bytes.Buffer
|
||||
writeNodeText(n, &b)
|
||||
return b.String()
|
||||
}
|
||||
|
||||
// nodeOwnText returns the contents of the text nodes that are direct
|
||||
// children of n.
|
||||
func nodeOwnText(n *html.Node) string {
|
||||
var b bytes.Buffer
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
if c.Type == html.TextNode {
|
||||
b.WriteString(c.Data)
|
||||
}
|
||||
}
|
||||
return b.String()
|
||||
}
|
||||
|
||||
// textSubstrSelector returns a selector that matches nodes that
|
||||
// contain the given text.
|
||||
func textSubstrSelector(val string) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
text := strings.ToLower(nodeText(n))
|
||||
return strings.Contains(text, val)
|
||||
}
|
||||
}
|
||||
|
||||
// ownTextSubstrSelector returns a selector that matches nodes that
|
||||
// directly contain the given text
|
||||
func ownTextSubstrSelector(val string) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
text := strings.ToLower(nodeOwnText(n))
|
||||
return strings.Contains(text, val)
|
||||
}
|
||||
}
|
||||
|
||||
// textRegexSelector returns a selector that matches nodes whose text matches
|
||||
// the specified regular expression
|
||||
func textRegexSelector(rx *regexp.Regexp) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
return rx.MatchString(nodeText(n))
|
||||
}
|
||||
}
|
||||
|
||||
// ownTextRegexSelector returns a selector that matches nodes whose text
|
||||
// directly matches the specified regular expression
|
||||
func ownTextRegexSelector(rx *regexp.Regexp) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
return rx.MatchString(nodeOwnText(n))
|
||||
}
|
||||
}
|
||||
|
||||
// hasChildSelector returns a selector that matches elements
|
||||
// with a child that matches a.
|
||||
func hasChildSelector(a Selector) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
if n.Type != html.ElementNode {
|
||||
return false
|
||||
}
|
||||
return hasChildMatch(n, a)
|
||||
}
|
||||
}
|
||||
|
||||
// hasDescendantSelector returns a selector that matches elements
|
||||
// with any descendant that matches a.
|
||||
func hasDescendantSelector(a Selector) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
if n.Type != html.ElementNode {
|
||||
return false
|
||||
}
|
||||
return hasDescendantMatch(n, a)
|
||||
}
|
||||
}
|
||||
|
||||
// nthChildSelector returns a selector that implements :nth-child(an+b).
|
||||
// If last is true, implements :nth-last-child instead.
|
||||
// If ofType is true, implements :nth-of-type instead.
|
||||
func nthChildSelector(a, b int, last, ofType bool) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
if n.Type != html.ElementNode {
|
||||
return false
|
||||
}
|
||||
|
||||
parent := n.Parent
|
||||
if parent == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
if parent.Type == html.DocumentNode {
|
||||
return false
|
||||
}
|
||||
|
||||
i := -1
|
||||
count := 0
|
||||
for c := parent.FirstChild; c != nil; c = c.NextSibling {
|
||||
if (c.Type != html.ElementNode) || (ofType && c.Data != n.Data) {
|
||||
continue
|
||||
}
|
||||
count++
|
||||
if c == n {
|
||||
i = count
|
||||
if !last {
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if i == -1 {
|
||||
// This shouldn't happen, since n should always be one of its parent's children.
|
||||
return false
|
||||
}
|
||||
|
||||
if last {
|
||||
i = count - i + 1
|
||||
}
|
||||
|
||||
i -= b
|
||||
if a == 0 {
|
||||
return i == 0
|
||||
}
|
||||
|
||||
return i%a == 0 && i/a >= 0
|
||||
}
|
||||
}
|
||||
|
||||
// simpleNthChildSelector returns a selector that implements :nth-child(b).
|
||||
// If ofType is true, implements :nth-of-type instead.
|
||||
func simpleNthChildSelector(b int, ofType bool) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
if n.Type != html.ElementNode {
|
||||
return false
|
||||
}
|
||||
|
||||
parent := n.Parent
|
||||
if parent == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
if parent.Type == html.DocumentNode {
|
||||
return false
|
||||
}
|
||||
|
||||
count := 0
|
||||
for c := parent.FirstChild; c != nil; c = c.NextSibling {
|
||||
if c.Type != html.ElementNode || (ofType && c.Data != n.Data) {
|
||||
continue
|
||||
}
|
||||
count++
|
||||
if c == n {
|
||||
return count == b
|
||||
}
|
||||
if count >= b {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
// simpleNthLastChildSelector returns a selector that implements
|
||||
// :nth-last-child(b). If ofType is true, implements :nth-last-of-type
|
||||
// instead.
|
||||
func simpleNthLastChildSelector(b int, ofType bool) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
if n.Type != html.ElementNode {
|
||||
return false
|
||||
}
|
||||
|
||||
parent := n.Parent
|
||||
if parent == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
if parent.Type == html.DocumentNode {
|
||||
return false
|
||||
}
|
||||
|
||||
count := 0
|
||||
for c := parent.LastChild; c != nil; c = c.PrevSibling {
|
||||
if c.Type != html.ElementNode || (ofType && c.Data != n.Data) {
|
||||
continue
|
||||
}
|
||||
count++
|
||||
if c == n {
|
||||
return count == b
|
||||
}
|
||||
if count >= b {
|
||||
return false
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
// onlyChildSelector returns a selector that implements :only-child.
|
||||
// If ofType is true, it implements :only-of-type instead.
|
||||
func onlyChildSelector(ofType bool) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
if n.Type != html.ElementNode {
|
||||
return false
|
||||
}
|
||||
|
||||
parent := n.Parent
|
||||
if parent == nil {
|
||||
return false
|
||||
}
|
||||
|
||||
if parent.Type == html.DocumentNode {
|
||||
return false
|
||||
}
|
||||
|
||||
count := 0
|
||||
for c := parent.FirstChild; c != nil; c = c.NextSibling {
|
||||
if (c.Type != html.ElementNode) || (ofType && c.Data != n.Data) {
|
||||
continue
|
||||
}
|
||||
count++
|
||||
if count > 1 {
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
return count == 1
|
||||
}
|
||||
}
|
||||
|
||||
// inputSelector is a Selector that matches input, select, textarea and button elements.
|
||||
func inputSelector(n *html.Node) bool {
|
||||
return n.Type == html.ElementNode && (n.Data == "input" || n.Data == "select" || n.Data == "textarea" || n.Data == "button")
|
||||
}
|
||||
|
||||
// emptyElementSelector is a Selector that matches empty elements.
|
||||
func emptyElementSelector(n *html.Node) bool {
|
||||
if n.Type != html.ElementNode {
|
||||
return false
|
||||
}
|
||||
|
||||
for c := n.FirstChild; c != nil; c = c.NextSibling {
|
||||
switch c.Type {
|
||||
case html.ElementNode, html.TextNode:
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
return true
|
||||
}
|
||||
|
||||
// descendantSelector returns a Selector that matches an element if
|
||||
// it matches d and has an ancestor that matches a.
|
||||
func descendantSelector(a, d Selector) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
if !d(n) {
|
||||
return false
|
||||
}
|
||||
|
||||
for p := n.Parent; p != nil; p = p.Parent {
|
||||
if a(p) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
// childSelector returns a Selector that matches an element if
|
||||
// it matches d and its parent matches a.
|
||||
func childSelector(a, d Selector) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
return d(n) && n.Parent != nil && a(n.Parent)
|
||||
}
|
||||
}
|
||||
|
||||
// siblingSelector returns a Selector that matches an element
|
||||
// if it matches s2 and in is preceded by an element that matches s1.
|
||||
// If adjacent is true, the sibling must be immediately before the element.
|
||||
func siblingSelector(s1, s2 Selector, adjacent bool) Selector {
|
||||
return func(n *html.Node) bool {
|
||||
if !s2(n) {
|
||||
return false
|
||||
}
|
||||
|
||||
if adjacent {
|
||||
for n = n.PrevSibling; n != nil; n = n.PrevSibling {
|
||||
if n.Type == html.TextNode || n.Type == html.CommentNode {
|
||||
continue
|
||||
}
|
||||
return s1(n)
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
// Walk backwards looking for element that matches s1
|
||||
for c := n.PrevSibling; c != nil; c = c.PrevSibling {
|
||||
if s1(c) {
|
||||
return true
|
||||
}
|
||||
}
|
||||
|
||||
return false
|
||||
}
|
||||
}
|
||||
|
||||
// rootSelector implements :root
|
||||
func rootSelector(n *html.Node) bool {
|
||||
if n.Type != html.ElementNode {
|
||||
return false
|
||||
}
|
||||
if n.Parent == nil {
|
||||
return false
|
||||
}
|
||||
return n.Parent.Type == html.DocumentNode
|
||||
}
|
||||
|
|
@ -1,32 +0,0 @@
|
|||
# vscode
|
||||
.vscode
|
||||
debug
|
||||
*.test
|
||||
|
||||
./build
|
||||
|
||||
# Compiled Object files, Static and Dynamic libs (Shared Objects)
|
||||
*.o
|
||||
*.a
|
||||
*.so
|
||||
|
||||
|
||||
# Folders
|
||||
_obj
|
||||
_test
|
||||
|
||||
# Architecture specific extensions/prefixes
|
||||
*.[568vq]
|
||||
[568vq].out
|
||||
|
||||
*.cgo1.go
|
||||
*.cgo2.c
|
||||
_cgo_defun.c
|
||||
_cgo_gotypes.go
|
||||
_cgo_export.*
|
||||
|
||||
_testmain.go
|
||||
|
||||
*.exe
|
||||
*.test
|
||||
*.prof
|
||||
|
|
@ -1,15 +0,0 @@
|
|||
language: go
|
||||
|
||||
go:
|
||||
- 1.6
|
||||
- 1.7
|
||||
- 1.8
|
||||
|
||||
install:
|
||||
- go get golang.org/x/net/html/charset
|
||||
- go get golang.org/x/net/html
|
||||
- go get github.com/antchfx/xpath
|
||||
- go get github.com/mattn/goveralls
|
||||
|
||||
script:
|
||||
- $HOME/gopath/bin/goveralls -service=travis-ci
|
||||
|
|
@ -1,17 +0,0 @@
|
|||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in
|
||||
all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
||||
THE SOFTWARE.
|
||||
|
|
@ -1,102 +0,0 @@
|
|||
htmlquery
|
||||
====
|
||||
[](https://travis-ci.org/antchfx/htmlquery)
|
||||
[](https://coveralls.io/github/antchfx/htmlquery?branch=master)
|
||||
[](https://godoc.org/github.com/antchfx/htmlquery)
|
||||
[](https://goreportcard.com/report/github.com/antchfx/htmlquery)
|
||||
|
||||
Overview
|
||||
====
|
||||
|
||||
htmlquery is an XPath query package for HTML, lets you extract data or evaluate from HTML documents by an XPath expression.
|
||||
|
||||
Changelogs
|
||||
===
|
||||
|
||||
2019-02-04
|
||||
- [#7](https://github.com/antchfx/htmlquery/issues/7) Removed deprecated `FindEach()` and `FindEachWithBreak()` methods.
|
||||
|
||||
2018-12-28
|
||||
- Avoid adding duplicate elements to list for `Find()` method. [#6](https://github.com/antchfx/htmlquery/issues/6)
|
||||
|
||||
Installation
|
||||
====
|
||||
|
||||
> $ go get github.com/antchfx/htmlquery
|
||||
|
||||
Getting Started
|
||||
====
|
||||
|
||||
#### Load HTML document from URL.
|
||||
|
||||
```go
|
||||
doc, err := htmlquery.LoadURL("http://example.com/")
|
||||
```
|
||||
|
||||
#### Load HTML document from string.
|
||||
|
||||
```go
|
||||
s := `<html>....</html>`
|
||||
doc, err := htmlquery.Parse(strings.NewReader(s))
|
||||
```
|
||||
|
||||
#### Find all A elements.
|
||||
|
||||
```go
|
||||
list := htmlquery.Find(doc, "//a")
|
||||
```
|
||||
|
||||
#### Find all A elements that have `href` attribute.
|
||||
|
||||
```go
|
||||
list := range htmlquery.Find(doc, "//a[@href]")
|
||||
```
|
||||
|
||||
#### Find all A elements and only get `href` attribute self.
|
||||
|
||||
```go
|
||||
list := range htmlquery.Find(doc, "//a/@href")
|
||||
```
|
||||
|
||||
### Find the third A element.
|
||||
|
||||
```go
|
||||
a := htmlquery.FindOne(doc, "//a[3]")
|
||||
```
|
||||
|
||||
#### Evaluate the number of all IMG element.
|
||||
|
||||
```go
|
||||
expr, _ := xpath.Compile("count(//img)")
|
||||
v := expr.Evaluate(htmlquery.CreateXPathNavigator(doc)).(float64)
|
||||
fmt.Printf("total count is %f", v)
|
||||
```
|
||||
|
||||
Quick Tutorial
|
||||
===
|
||||
|
||||
```go
|
||||
func main() {
|
||||
doc, err := htmlquery.LoadURL("https://www.bing.com/search?q=golang")
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
// Find all news item.
|
||||
for i, n := range htmlquery.Find(doc, "//ol/li") {
|
||||
a := htmlquery.FindOne(n, "//a")
|
||||
fmt.Printf("%d %s(%s)\n", i, htmlquery.InnerText(a), htmlquery.SelectAttr(a, "href"))
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
List of supported XPath query packages
|
||||
===
|
||||
|Name |Description |
|
||||
|--------------------------|----------------|
|
||||
|[htmlquery](https://github.com/antchfx/htmlquery) | XPath query package for the HTML document|
|
||||
|[xmlquery](https://github.com/antchfx/xmlquery) | XPath query package for the XML document|
|
||||
|[jsonquery](https://github.com/antchfx/jsonquery) | XPath query package for the JSON document|
|
||||
|
||||
Questions
|
||||
===
|
||||
Please let me know if you have any questions.
|
||||
|
|
@ -1,291 +0,0 @@
|
|||
/*
|
||||
Package htmlquery provides extract data from HTML documents using XPath expression.
|
||||
*/
|
||||
package htmlquery
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"io"
|
||||
"net/http"
|
||||
|
||||
"github.com/antchfx/xpath"
|
||||
"golang.org/x/net/html"
|
||||
"golang.org/x/net/html/charset"
|
||||
)
|
||||
|
||||
var _ xpath.NodeNavigator = &NodeNavigator{}
|
||||
|
||||
// CreateXPathNavigator creates a new xpath.NodeNavigator for the specified html.Node.
|
||||
func CreateXPathNavigator(top *html.Node) *NodeNavigator {
|
||||
return &NodeNavigator{curr: top, root: top, attr: -1}
|
||||
}
|
||||
|
||||
// Find searches the html.Node that matches by the specified XPath expr.
|
||||
func Find(top *html.Node, expr string) []*html.Node {
|
||||
exp, err := xpath.Compile(expr)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
var elems []*html.Node
|
||||
t := exp.Select(CreateXPathNavigator(top))
|
||||
for t.MoveNext() {
|
||||
nav := t.Current().(*NodeNavigator)
|
||||
n := getCurrentNode(nav)
|
||||
// avoid adding duplicate nodes.
|
||||
if len(elems) > 0 && (elems[0] == n || (nav.NodeType() == xpath.AttributeNode &&
|
||||
nav.LocalName() == elems[0].Data && nav.Value() == InnerText(elems[0]))) {
|
||||
continue
|
||||
}
|
||||
elems = append(elems, n)
|
||||
}
|
||||
return elems
|
||||
}
|
||||
|
||||
// FindOne searches the html.Node that matches by the specified XPath expr,
|
||||
// and returns first element of matched html.Node.
|
||||
func FindOne(top *html.Node, expr string) *html.Node {
|
||||
var elem *html.Node
|
||||
exp, err := xpath.Compile(expr)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
t := exp.Select(CreateXPathNavigator(top))
|
||||
if t.MoveNext() {
|
||||
elem = getCurrentNode(t.Current().(*NodeNavigator))
|
||||
}
|
||||
return elem
|
||||
}
|
||||
|
||||
// LoadURL loads the HTML document from the specified URL.
|
||||
func LoadURL(url string) (*html.Node, error) {
|
||||
resp, err := http.Get(url)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
|
||||
r, err := charset.NewReader(resp.Body, resp.Header.Get("Content-Type"))
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return html.Parse(r)
|
||||
}
|
||||
|
||||
func getCurrentNode(n *NodeNavigator) *html.Node {
|
||||
if n.NodeType() == xpath.AttributeNode {
|
||||
childNode := &html.Node{
|
||||
Type: html.TextNode,
|
||||
Data: n.Value(),
|
||||
}
|
||||
return &html.Node{
|
||||
Type: html.ElementNode,
|
||||
Data: n.LocalName(),
|
||||
FirstChild: childNode,
|
||||
LastChild: childNode,
|
||||
}
|
||||
|
||||
}
|
||||
return n.curr
|
||||
}
|
||||
|
||||
// Parse returns the parse tree for the HTML from the given Reader.
|
||||
func Parse(r io.Reader) (*html.Node, error) {
|
||||
return html.Parse(r)
|
||||
}
|
||||
|
||||
// InnerText returns the text between the start and end tags of the object.
|
||||
func InnerText(n *html.Node) string {
|
||||
var output func(*bytes.Buffer, *html.Node)
|
||||
output = func(buf *bytes.Buffer, n *html.Node) {
|
||||
switch n.Type {
|
||||
case html.TextNode:
|
||||
buf.WriteString(n.Data)
|
||||
return
|
||||
case html.CommentNode:
|
||||
return
|
||||
}
|
||||
for child := n.FirstChild; child != nil; child = child.NextSibling {
|
||||
output(buf, child)
|
||||
}
|
||||
}
|
||||
|
||||
var buf bytes.Buffer
|
||||
output(&buf, n)
|
||||
return buf.String()
|
||||
}
|
||||
|
||||
// SelectAttr returns the attribute value with the specified name.
|
||||
func SelectAttr(n *html.Node, name string) (val string) {
|
||||
if n == nil {
|
||||
return
|
||||
}
|
||||
if n.Type == html.ElementNode && n.Parent == nil && name == n.Data {
|
||||
return InnerText(n)
|
||||
}
|
||||
for _, attr := range n.Attr {
|
||||
if attr.Key == name {
|
||||
val = attr.Val
|
||||
break
|
||||
}
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
// OutputHTML returns the text including tags name.
|
||||
func OutputHTML(n *html.Node, self bool) string {
|
||||
var buf bytes.Buffer
|
||||
if self {
|
||||
html.Render(&buf, n)
|
||||
} else {
|
||||
for n := n.FirstChild; n != nil; n = n.NextSibling {
|
||||
html.Render(&buf, n)
|
||||
}
|
||||
}
|
||||
return buf.String()
|
||||
}
|
||||
|
||||
type NodeNavigator struct {
|
||||
root, curr *html.Node
|
||||
attr int
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) Current() *html.Node {
|
||||
return h.curr
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) NodeType() xpath.NodeType {
|
||||
switch h.curr.Type {
|
||||
case html.CommentNode:
|
||||
return xpath.CommentNode
|
||||
case html.TextNode:
|
||||
return xpath.TextNode
|
||||
case html.DocumentNode:
|
||||
return xpath.RootNode
|
||||
case html.ElementNode:
|
||||
if h.attr != -1 {
|
||||
return xpath.AttributeNode
|
||||
}
|
||||
return xpath.ElementNode
|
||||
case html.DoctypeNode:
|
||||
// ignored <!DOCTYPE HTML> declare and as Root-Node type.
|
||||
return xpath.RootNode
|
||||
}
|
||||
panic(fmt.Sprintf("unknown HTML node type: %v", h.curr.Type))
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) LocalName() string {
|
||||
if h.attr != -1 {
|
||||
return h.curr.Attr[h.attr].Key
|
||||
}
|
||||
return h.curr.Data
|
||||
}
|
||||
|
||||
func (*NodeNavigator) Prefix() string {
|
||||
return ""
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) Value() string {
|
||||
switch h.curr.Type {
|
||||
case html.CommentNode:
|
||||
return h.curr.Data
|
||||
case html.ElementNode:
|
||||
if h.attr != -1 {
|
||||
return h.curr.Attr[h.attr].Val
|
||||
}
|
||||
return InnerText(h.curr)
|
||||
case html.TextNode:
|
||||
return h.curr.Data
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) Copy() xpath.NodeNavigator {
|
||||
n := *h
|
||||
return &n
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) MoveToRoot() {
|
||||
h.curr = h.root
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) MoveToParent() bool {
|
||||
if h.attr != -1 {
|
||||
h.attr = -1
|
||||
return true
|
||||
} else if node := h.curr.Parent; node != nil {
|
||||
h.curr = node
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) MoveToNextAttribute() bool {
|
||||
if h.attr >= len(h.curr.Attr)-1 {
|
||||
return false
|
||||
}
|
||||
h.attr++
|
||||
return true
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) MoveToChild() bool {
|
||||
if h.attr != -1 {
|
||||
return false
|
||||
}
|
||||
if node := h.curr.FirstChild; node != nil {
|
||||
h.curr = node
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) MoveToFirst() bool {
|
||||
if h.attr != -1 || h.curr.PrevSibling == nil {
|
||||
return false
|
||||
}
|
||||
for {
|
||||
node := h.curr.PrevSibling
|
||||
if node == nil {
|
||||
break
|
||||
}
|
||||
h.curr = node
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) String() string {
|
||||
return h.Value()
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) MoveToNext() bool {
|
||||
if h.attr != -1 {
|
||||
return false
|
||||
}
|
||||
if node := h.curr.NextSibling; node != nil {
|
||||
h.curr = node
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) MoveToPrevious() bool {
|
||||
if h.attr != -1 {
|
||||
return false
|
||||
}
|
||||
if node := h.curr.PrevSibling; node != nil {
|
||||
h.curr = node
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func (h *NodeNavigator) MoveTo(other xpath.NodeNavigator) bool {
|
||||
node, ok := other.(*NodeNavigator)
|
||||
if !ok || node.root != h.root {
|
||||
return false
|
||||
}
|
||||
|
||||
h.curr = node.curr
|
||||
h.attr = node.attr
|
||||
return true
|
||||
}
|
||||
|
|
@ -1,32 +0,0 @@
|
|||
# vscode
|
||||
.vscode
|
||||
debug
|
||||
*.test
|
||||
|
||||
./build
|
||||
|
||||
# Compiled Object files, Static and Dynamic libs (Shared Objects)
|
||||
*.o
|
||||
*.a
|
||||
*.so
|
||||
|
||||
|
||||
# Folders
|
||||
_obj
|
||||
_test
|
||||
|
||||
# Architecture specific extensions/prefixes
|
||||
*.[568vq]
|
||||
[568vq].out
|
||||
|
||||
*.cgo1.go
|
||||
*.cgo2.c
|
||||
_cgo_defun.c
|
||||
_cgo_gotypes.go
|
||||
_cgo_export.*
|
||||
|
||||
_testmain.go
|
||||
|
||||
*.exe
|
||||
*.test
|
||||
*.prof
|
||||
|
|
@ -1,14 +0,0 @@
|
|||
language: go
|
||||
|
||||
go:
|
||||
- 1.6
|
||||
- 1.7
|
||||
- 1.8
|
||||
|
||||
install:
|
||||
- go get golang.org/x/net/html/charset
|
||||
- go get github.com/antchfx/xpath
|
||||
- go get github.com/mattn/goveralls
|
||||
|
||||
script:
|
||||
- $HOME/gopath/bin/goveralls -service=travis-ci
|
||||
|
|
@ -1,17 +0,0 @@
|
|||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in
|
||||
all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
||||
THE SOFTWARE.
|
||||
|
|
@ -1,186 +0,0 @@
|
|||
xmlquery
|
||||
====
|
||||
[](https://travis-ci.org/antchfx/xmlquery)
|
||||
[](https://coveralls.io/github/antchfx/xmlquery?branch=master)
|
||||
[](https://godoc.org/github.com/antchfx/xmlquery)
|
||||
[](https://goreportcard.com/report/github.com/antchfx/xmlquery)
|
||||
|
||||
Overview
|
||||
===
|
||||
|
||||
xmlquery is an XPath query package for XML document, lets you extract data or evaluate from XML documents by an XPath expression.
|
||||
|
||||
Change Logs
|
||||
===
|
||||
|
||||
**2018-12-23**
|
||||
* added XML output will including comment node. [#9](https://github.com/antchfx/xmlquery/issues/9)
|
||||
|
||||
**2018-12-03**
|
||||
* added support attribute name with namespace prefix and XML output. [#6](https://github.com/antchfx/xmlquery/issues/6)
|
||||
|
||||
Installation
|
||||
====
|
||||
|
||||
> $ go get github.com/antchfx/xmlquery
|
||||
|
||||
Getting Started
|
||||
===
|
||||
|
||||
#### Parse a XML from URL.
|
||||
|
||||
```go
|
||||
doc, err := xmlquery.LoadURL("http://www.example.com/sitemap.xml")
|
||||
```
|
||||
|
||||
#### Parse a XML from string.
|
||||
|
||||
```go
|
||||
s := `<?xml version="1.0" encoding="utf-8"?><rss version="2.0"></rss>`
|
||||
doc, err := xmlquery.Parse(strings.NewReader(s))
|
||||
```
|
||||
|
||||
#### Parse a XML from io.Reader.
|
||||
|
||||
```go
|
||||
f, err := os.Open("../books.xml")
|
||||
doc, err := xmlquery.Parse(f)
|
||||
```
|
||||
|
||||
#### Find authors of all books in the bookstore.
|
||||
|
||||
```go
|
||||
list := xmlquery.Find(doc, "//book//author")
|
||||
// or
|
||||
list := xmlquery.Find(doc, "//author")
|
||||
```
|
||||
|
||||
#### Find the second book.
|
||||
|
||||
```go
|
||||
book := xmlquery.FindOne(doc, "//book[2]")
|
||||
```
|
||||
|
||||
#### Find all book elements and only get `id` attribute self. (New Feature)
|
||||
|
||||
```go
|
||||
list := xmlquery.Find(doc,"//book/@id")
|
||||
```
|
||||
|
||||
#### Find all books with id is bk104.
|
||||
|
||||
```go
|
||||
list := xmlquery.Find(doc, "//book[@id='bk104']")
|
||||
```
|
||||
|
||||
#### Find all books that price less than 5.
|
||||
|
||||
```go
|
||||
list := xmlquery.Find(doc, "//book[price<5]")
|
||||
```
|
||||
|
||||
#### Evaluate the total price of all books.
|
||||
|
||||
```go
|
||||
expr, err := xpath.Compile("sum(//book/price)")
|
||||
price := expr.Evaluate(xmlquery.CreateXPathNavigator(doc)).(float64)
|
||||
fmt.Printf("total price: %f\n", price)
|
||||
```
|
||||
|
||||
#### Evaluate the number of all books element.
|
||||
|
||||
```go
|
||||
expr, err := xpath.Compile("count(//book)")
|
||||
price := expr.Evaluate(xmlquery.CreateXPathNavigator(doc)).(float64)
|
||||
```
|
||||
|
||||
#### Create XML document.
|
||||
|
||||
```go
|
||||
doc := &xmlquery.Node{
|
||||
Type: xmlquery.DeclarationNode,
|
||||
Data: "xml",
|
||||
Attr: []xml.Attr{
|
||||
xml.Attr{Name: xml.Name{Local: "version"}, Value: "1.0"},
|
||||
},
|
||||
}
|
||||
root := &xmlquery.Node{
|
||||
Data: "rss",
|
||||
Type: xmlquery.ElementNode,
|
||||
}
|
||||
doc.FirstChild = root
|
||||
channel := &xmlquery.Node{
|
||||
Data: "channel",
|
||||
Type: xmlquery.ElementNode,
|
||||
}
|
||||
root.FirstChild = channel
|
||||
title := &xmlquery.Node{
|
||||
Data: "title",
|
||||
Type: xmlquery.ElementNode,
|
||||
}
|
||||
title_text := &xmlquery.Node{
|
||||
Data: "W3Schools Home Page",
|
||||
Type: xmlquery.TextNode,
|
||||
}
|
||||
title.FirstChild = title_text
|
||||
channel.FirstChild = title
|
||||
fmt.Println(doc.OutputXML(true))
|
||||
// <?xml version="1.0"?><rss><channel><title>W3Schools Home Page</title></channel></rss>
|
||||
```
|
||||
|
||||
Quick Tutorial
|
||||
===
|
||||
|
||||
```go
|
||||
import (
|
||||
"github.com/antchfx/xmlquery"
|
||||
)
|
||||
|
||||
func main(){
|
||||
s := `<?xml version="1.0" encoding="UTF-8" ?>
|
||||
<rss version="2.0">
|
||||
<channel>
|
||||
<title>W3Schools Home Page</title>
|
||||
<link>https://www.w3schools.com</link>
|
||||
<description>Free web building tutorials</description>
|
||||
<item>
|
||||
<title>RSS Tutorial</title>
|
||||
<link>https://www.w3schools.com/xml/xml_rss.asp</link>
|
||||
<description>New RSS tutorial on W3Schools</description>
|
||||
</item>
|
||||
<item>
|
||||
<title>XML Tutorial</title>
|
||||
<link>https://www.w3schools.com/xml</link>
|
||||
<description>New XML tutorial on W3Schools</description>
|
||||
</item>
|
||||
</channel>
|
||||
</rss>`
|
||||
|
||||
doc, err := xmlquery.Parse(strings.NewReader(s))
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
channel := xmlquery.FindOne(doc, "//channel")
|
||||
if n := channel.SelectElement("title"); n != nil {
|
||||
fmt.Printf("title: %s\n", n.InnerText())
|
||||
}
|
||||
if n := channel.SelectElement("link"); n != nil {
|
||||
fmt.Printf("link: %s\n", n.InnerText())
|
||||
}
|
||||
for i, n := range xmlquery.Find(doc, "//item/title") {
|
||||
fmt.Printf("#%d %s\n", i, n.InnerText())
|
||||
}
|
||||
}
|
||||
```
|
||||
|
||||
List of supported XPath query packages
|
||||
===
|
||||
|Name |Description |
|
||||
|--------------------------|----------------|
|
||||
|[htmlquery](https://github.com/antchfx/htmlquery) | XPath query package for the HTML document|
|
||||
|[xmlquery](https://github.com/antchfx/xmlquery) | XPath query package for the XML document|
|
||||
|[jsonquery](https://github.com/antchfx/jsonquery) | XPath query package for the JSON document|
|
||||
|
||||
Questions
|
||||
===
|
||||
Please let me know if you have any questions
|
||||
|
|
@ -1,121 +0,0 @@
|
|||
<?xml version="1.0"?>
|
||||
<?xml-stylesheet type="text/xsl" ?>
|
||||
<bookstore specialty="novel">
|
||||
<book id="bk101">
|
||||
<author>Gambardella, Matthew</author>
|
||||
<title>XML Developer's Guide</title>
|
||||
<genre>Computer</genre>
|
||||
<price>44.95</price>
|
||||
<publish_date>2000-10-01</publish_date>
|
||||
<description>An in-depth look at creating applications
|
||||
with XML.</description>
|
||||
</book>
|
||||
<book id="bk102">
|
||||
<author>Ralls, Kim</author>
|
||||
<title>Midnight Rain</title>
|
||||
<genre>Fantasy</genre>
|
||||
<price>5.95</price>
|
||||
<publish_date>2000-12-16</publish_date>
|
||||
<description>A former architect battles corporate zombies,
|
||||
an evil sorceress, and her own childhood to become queen
|
||||
of the world.</description>
|
||||
</book>
|
||||
<book id="bk103">
|
||||
<author>Corets, Eva</author>
|
||||
<title>Maeve Ascendant</title>
|
||||
<genre>Fantasy</genre>
|
||||
<price>5.95</price>
|
||||
<publish_date>2000-11-17</publish_date>
|
||||
<description>After the collapse of a nanotechnology
|
||||
society in England, the young survivors lay the
|
||||
foundation for a new society.</description>
|
||||
</book>
|
||||
<book id="bk104">
|
||||
<author>Corets, Eva</author>
|
||||
<title>Oberon's Legacy</title>
|
||||
<genre>Fantasy</genre>
|
||||
<price>5.95</price>
|
||||
<publish_date>2001-03-10</publish_date>
|
||||
<description>In post-apocalypse England, the mysterious
|
||||
agent known only as Oberon helps to create a new life
|
||||
for the inhabitants of London. Sequel to Maeve
|
||||
Ascendant.</description>
|
||||
</book>
|
||||
<book id="bk105">
|
||||
<author>Corets, Eva</author>
|
||||
<title>The Sundered Grail</title>
|
||||
<genre>Fantasy</genre>
|
||||
<price>5.95</price>
|
||||
<publish_date>2001-09-10</publish_date>
|
||||
<description>The two daughters of Maeve, half-sisters,
|
||||
battle one another for control of England. Sequel to
|
||||
Oberon's Legacy.</description>
|
||||
</book>
|
||||
<book id="bk106">
|
||||
<author>Randall, Cynthia</author>
|
||||
<title>Lover Birds</title>
|
||||
<genre>Romance</genre>
|
||||
<price>4.95</price>
|
||||
<publish_date>2000-09-02</publish_date>
|
||||
<description>When Carla meets Paul at an ornithology
|
||||
conference, tempers fly as feathers get ruffled.</description>
|
||||
</book>
|
||||
<book id="bk107">
|
||||
<author>Thurman, Paula</author>
|
||||
<title>Splish Splash</title>
|
||||
<genre>Romance</genre>
|
||||
<price>4.95</price>
|
||||
<publish_date>2000-11-02</publish_date>
|
||||
<description>A deep sea diver finds true love twenty
|
||||
thousand leagues beneath the sea.</description>
|
||||
</book>
|
||||
<book id="bk108">
|
||||
<author>Knorr, Stefan</author>
|
||||
<title>Creepy Crawlies</title>
|
||||
<genre>Horror</genre>
|
||||
<price>4.95</price>
|
||||
<publish_date>2000-12-06</publish_date>
|
||||
<description>An anthology of horror stories about roaches,
|
||||
centipedes, scorpions and other insects.</description>
|
||||
</book>
|
||||
<book id="bk109">
|
||||
<author>Kress, Peter</author>
|
||||
<title>Paradox Lost</title>
|
||||
<genre>Science Fiction</genre>
|
||||
<price>6.95</price>
|
||||
<publish_date>2000-11-02</publish_date>
|
||||
<description>After an inadvertant trip through a Heisenberg
|
||||
Uncertainty Device, James Salway discovers the problems
|
||||
of being quantum.</description>
|
||||
</book>
|
||||
<book id="bk110">
|
||||
<author>O'Brien, Tim</author>
|
||||
<title>Microsoft .NET: The Programming Bible</title>
|
||||
<genre>Computer</genre>
|
||||
<price>36.95</price>
|
||||
<publish_date>2000-12-09</publish_date>
|
||||
<description>Microsoft's .NET initiative is explored in
|
||||
detail in this deep programmer's reference.</description>
|
||||
</book>
|
||||
<book id="bk111">
|
||||
<author>O'Brien, Tim</author>
|
||||
<title>MSXML3: A Comprehensive Guide</title>
|
||||
<genre>Computer</genre>
|
||||
<price>36.95</price>
|
||||
<publish_date>2000-12-01</publish_date>
|
||||
<description>The Microsoft MSXML3 parser is covered in
|
||||
detail, with attention to XML DOM interfaces, XSLT processing,
|
||||
SAX and more.</description>
|
||||
</book>
|
||||
<book id="bk112">
|
||||
<author>Galos, Mike</author>
|
||||
<title>Visual Studio 7: A Comprehensive Guide</title>
|
||||
<genre>Computer</genre>
|
||||
<price>49.95</price>
|
||||
<publish_date>2001-04-16</publish_date>
|
||||
<description>Microsoft Visual Studio 7 is explored in depth,
|
||||
looking at how Visual Basic, Visual C++, C#, and ASP+ are
|
||||
integrated into a comprehensive development
|
||||
environment.</description>
|
||||
</book>
|
||||
</bookstore>
|
||||
|
|
@ -1,302 +0,0 @@
|
|||
package xmlquery
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/xml"
|
||||
"errors"
|
||||
"fmt"
|
||||
"io"
|
||||
"net/http"
|
||||
"strings"
|
||||
|
||||
"golang.org/x/net/html/charset"
|
||||
)
|
||||
|
||||
// A NodeType is the type of a Node.
|
||||
type NodeType uint
|
||||
|
||||
const (
|
||||
// DocumentNode is a document object that, as the root of the document tree,
|
||||
// provides access to the entire XML document.
|
||||
DocumentNode NodeType = iota
|
||||
// DeclarationNode is the document type declaration, indicated by the following
|
||||
// tag (for example, <!DOCTYPE...> ).
|
||||
DeclarationNode
|
||||
// ElementNode is an element (for example, <item> ).
|
||||
ElementNode
|
||||
// TextNode is the text content of a node.
|
||||
TextNode
|
||||
// CommentNode a comment (for example, <!-- my comment --> ).
|
||||
CommentNode
|
||||
// AttributeNode is an attribute of element.
|
||||
AttributeNode
|
||||
)
|
||||
|
||||
// A Node consists of a NodeType and some Data (tag name for
|
||||
// element nodes, content for text) and are part of a tree of Nodes.
|
||||
type Node struct {
|
||||
Parent, FirstChild, LastChild, PrevSibling, NextSibling *Node
|
||||
|
||||
Type NodeType
|
||||
Data string
|
||||
Prefix string
|
||||
NamespaceURI string
|
||||
Attr []xml.Attr
|
||||
|
||||
level int // node level in the tree
|
||||
}
|
||||
|
||||
// InnerText returns the text between the start and end tags of the object.
|
||||
func (n *Node) InnerText() string {
|
||||
var output func(*bytes.Buffer, *Node)
|
||||
output = func(buf *bytes.Buffer, n *Node) {
|
||||
switch n.Type {
|
||||
case TextNode:
|
||||
buf.WriteString(n.Data)
|
||||
return
|
||||
case CommentNode:
|
||||
return
|
||||
}
|
||||
for child := n.FirstChild; child != nil; child = child.NextSibling {
|
||||
output(buf, child)
|
||||
}
|
||||
}
|
||||
|
||||
var buf bytes.Buffer
|
||||
output(&buf, n)
|
||||
return buf.String()
|
||||
}
|
||||
|
||||
func outputXML(buf *bytes.Buffer, n *Node) {
|
||||
if n.Type == TextNode {
|
||||
xml.EscapeText(buf, []byte(strings.TrimSpace(n.Data)))
|
||||
return
|
||||
}
|
||||
if n.Type == CommentNode {
|
||||
buf.WriteString("<!--")
|
||||
buf.WriteString(n.Data)
|
||||
buf.WriteString("-->")
|
||||
return
|
||||
}
|
||||
if n.Type == DeclarationNode {
|
||||
buf.WriteString("<?" + n.Data)
|
||||
} else {
|
||||
if n.Prefix == "" {
|
||||
buf.WriteString("<" + n.Data)
|
||||
} else {
|
||||
buf.WriteString("<" + n.Prefix + ":" + n.Data)
|
||||
}
|
||||
}
|
||||
|
||||
for _, attr := range n.Attr {
|
||||
if attr.Name.Space != "" {
|
||||
buf.WriteString(fmt.Sprintf(` %s:%s="%s"`, attr.Name.Space, attr.Name.Local, attr.Value))
|
||||
} else {
|
||||
buf.WriteString(fmt.Sprintf(` %s="%s"`, attr.Name.Local, attr.Value))
|
||||
}
|
||||
}
|
||||
if n.Type == DeclarationNode {
|
||||
buf.WriteString("?>")
|
||||
} else {
|
||||
buf.WriteString(">")
|
||||
}
|
||||
for child := n.FirstChild; child != nil; child = child.NextSibling {
|
||||
outputXML(buf, child)
|
||||
}
|
||||
if n.Type != DeclarationNode {
|
||||
if n.Prefix == "" {
|
||||
buf.WriteString(fmt.Sprintf("</%s>", n.Data))
|
||||
} else {
|
||||
buf.WriteString(fmt.Sprintf("</%s:%s>", n.Prefix, n.Data))
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
// OutputXML returns the text that including tags name.
|
||||
func (n *Node) OutputXML(self bool) string {
|
||||
var buf bytes.Buffer
|
||||
if self {
|
||||
outputXML(&buf, n)
|
||||
} else {
|
||||
for n := n.FirstChild; n != nil; n = n.NextSibling {
|
||||
outputXML(&buf, n)
|
||||
}
|
||||
}
|
||||
|
||||
return buf.String()
|
||||
}
|
||||
|
||||
func addAttr(n *Node, key, val string) {
|
||||
var attr xml.Attr
|
||||
if i := strings.Index(key, ":"); i > 0 {
|
||||
attr = xml.Attr{
|
||||
Name: xml.Name{Space: key[:i], Local: key[i+1:]},
|
||||
Value: val,
|
||||
}
|
||||
} else {
|
||||
attr = xml.Attr{
|
||||
Name: xml.Name{Local: key},
|
||||
Value: val,
|
||||
}
|
||||
}
|
||||
|
||||
n.Attr = append(n.Attr, attr)
|
||||
}
|
||||
|
||||
func addChild(parent, n *Node) {
|
||||
n.Parent = parent
|
||||
if parent.FirstChild == nil {
|
||||
parent.FirstChild = n
|
||||
} else {
|
||||
parent.LastChild.NextSibling = n
|
||||
n.PrevSibling = parent.LastChild
|
||||
}
|
||||
|
||||
parent.LastChild = n
|
||||
}
|
||||
|
||||
func addSibling(sibling, n *Node) {
|
||||
for t := sibling.NextSibling; t != nil; t = t.NextSibling {
|
||||
sibling = t
|
||||
}
|
||||
n.Parent = sibling.Parent
|
||||
sibling.NextSibling = n
|
||||
n.PrevSibling = sibling
|
||||
if sibling.Parent != nil {
|
||||
sibling.Parent.LastChild = n
|
||||
}
|
||||
}
|
||||
|
||||
// LoadURL loads the XML document from the specified URL.
|
||||
func LoadURL(url string) (*Node, error) {
|
||||
resp, err := http.Get(url)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
defer resp.Body.Close()
|
||||
return parse(resp.Body)
|
||||
}
|
||||
|
||||
func parse(r io.Reader) (*Node, error) {
|
||||
var (
|
||||
decoder = xml.NewDecoder(r)
|
||||
doc = &Node{Type: DocumentNode}
|
||||
space2prefix = make(map[string]string)
|
||||
level = 0
|
||||
)
|
||||
// http://www.w3.org/XML/1998/namespace is bound by definition to the prefix xml.
|
||||
space2prefix["http://www.w3.org/XML/1998/namespace"] = "xml"
|
||||
decoder.CharsetReader = charset.NewReaderLabel
|
||||
prev := doc
|
||||
for {
|
||||
tok, err := decoder.Token()
|
||||
switch {
|
||||
case err == io.EOF:
|
||||
goto quit
|
||||
case err != nil:
|
||||
return nil, err
|
||||
}
|
||||
|
||||
switch tok := tok.(type) {
|
||||
case xml.StartElement:
|
||||
if level == 0 {
|
||||
// mising XML declaration
|
||||
node := &Node{Type: DeclarationNode, Data: "xml", level: 1}
|
||||
addChild(prev, node)
|
||||
level = 1
|
||||
prev = node
|
||||
}
|
||||
// https://www.w3.org/TR/xml-names/#scoping-defaulting
|
||||
for _, att := range tok.Attr {
|
||||
if att.Name.Local == "xmlns" {
|
||||
space2prefix[att.Value] = ""
|
||||
} else if att.Name.Space == "xmlns" {
|
||||
space2prefix[att.Value] = att.Name.Local
|
||||
}
|
||||
}
|
||||
|
||||
if tok.Name.Space != "" {
|
||||
if _, found := space2prefix[tok.Name.Space]; !found {
|
||||
return nil, errors.New("xmlquery: invalid XML document, namespace is missing")
|
||||
}
|
||||
}
|
||||
|
||||
for i := 0; i < len(tok.Attr); i++ {
|
||||
att := &tok.Attr[i]
|
||||
if prefix, ok := space2prefix[att.Name.Space]; ok {
|
||||
att.Name.Space = prefix
|
||||
}
|
||||
}
|
||||
|
||||
node := &Node{
|
||||
Type: ElementNode,
|
||||
Data: tok.Name.Local,
|
||||
Prefix: space2prefix[tok.Name.Space],
|
||||
NamespaceURI: tok.Name.Space,
|
||||
Attr: tok.Attr,
|
||||
level: level,
|
||||
}
|
||||
//fmt.Println(fmt.Sprintf("start > %s : %d", node.Data, level))
|
||||
if level == prev.level {
|
||||
addSibling(prev, node)
|
||||
} else if level > prev.level {
|
||||
addChild(prev, node)
|
||||
} else if level < prev.level {
|
||||
for i := prev.level - level; i > 1; i-- {
|
||||
prev = prev.Parent
|
||||
}
|
||||
addSibling(prev.Parent, node)
|
||||
}
|
||||
prev = node
|
||||
level++
|
||||
case xml.EndElement:
|
||||
level--
|
||||
case xml.CharData:
|
||||
node := &Node{Type: TextNode, Data: string(tok), level: level}
|
||||
if level == prev.level {
|
||||
addSibling(prev, node)
|
||||
} else if level > prev.level {
|
||||
addChild(prev, node)
|
||||
}
|
||||
case xml.Comment:
|
||||
node := &Node{Type: CommentNode, Data: string(tok), level: level}
|
||||
if level == prev.level {
|
||||
addSibling(prev, node)
|
||||
} else if level > prev.level {
|
||||
addChild(prev, node)
|
||||
} else if level < prev.level {
|
||||
for i := prev.level - level; i > 1; i-- {
|
||||
prev = prev.Parent
|
||||
}
|
||||
addSibling(prev.Parent, node)
|
||||
}
|
||||
case xml.ProcInst: // Processing Instruction
|
||||
if prev.Type != DeclarationNode {
|
||||
level++
|
||||
}
|
||||
node := &Node{Type: DeclarationNode, Data: tok.Target, level: level}
|
||||
pairs := strings.Split(string(tok.Inst), " ")
|
||||
for _, pair := range pairs {
|
||||
pair = strings.TrimSpace(pair)
|
||||
if i := strings.Index(pair, "="); i > 0 {
|
||||
addAttr(node, pair[:i], strings.Trim(pair[i+1:], `"`))
|
||||
}
|
||||
}
|
||||
if level == prev.level {
|
||||
addSibling(prev, node)
|
||||
} else if level > prev.level {
|
||||
addChild(prev, node)
|
||||
}
|
||||
prev = node
|
||||
case xml.Directive:
|
||||
}
|
||||
|
||||
}
|
||||
quit:
|
||||
return doc, nil
|
||||
}
|
||||
|
||||
// Parse returns the parse tree for the XML from the given Reader.
|
||||
func Parse(r io.Reader) (*Node, error) {
|
||||
return parse(r)
|
||||
}
|
||||
|
|
@ -1,264 +0,0 @@
|
|||
/*
|
||||
Package xmlquery provides extract data from XML documents using XPath expression.
|
||||
*/
|
||||
package xmlquery
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"strings"
|
||||
|
||||
"github.com/antchfx/xpath"
|
||||
)
|
||||
|
||||
// SelectElements finds child elements with the specified name.
|
||||
func (n *Node) SelectElements(name string) []*Node {
|
||||
return Find(n, name)
|
||||
}
|
||||
|
||||
// SelectElement finds child elements with the specified name.
|
||||
func (n *Node) SelectElement(name string) *Node {
|
||||
return FindOne(n, name)
|
||||
}
|
||||
|
||||
// SelectAttr returns the attribute value with the specified name.
|
||||
func (n *Node) SelectAttr(name string) string {
|
||||
if n.Type == AttributeNode {
|
||||
if n.Data == name {
|
||||
return n.InnerText()
|
||||
}
|
||||
return ""
|
||||
}
|
||||
var local, space string
|
||||
local = name
|
||||
if i := strings.Index(name, ":"); i > 0 {
|
||||
space = name[:i]
|
||||
local = name[i+1:]
|
||||
}
|
||||
for _, attr := range n.Attr {
|
||||
if attr.Name.Local == local && attr.Name.Space == space {
|
||||
return attr.Value
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
var _ xpath.NodeNavigator = &NodeNavigator{}
|
||||
|
||||
// CreateXPathNavigator creates a new xpath.NodeNavigator for the specified html.Node.
|
||||
func CreateXPathNavigator(top *Node) *NodeNavigator {
|
||||
return &NodeNavigator{curr: top, root: top, attr: -1}
|
||||
}
|
||||
|
||||
func getCurrentNode(it *xpath.NodeIterator) *Node {
|
||||
n := it.Current().(*NodeNavigator)
|
||||
if n.NodeType() == xpath.AttributeNode {
|
||||
childNode := &Node{
|
||||
Type: TextNode,
|
||||
Data: n.Value(),
|
||||
}
|
||||
return &Node{
|
||||
Type: AttributeNode,
|
||||
Data: n.LocalName(),
|
||||
FirstChild: childNode,
|
||||
LastChild: childNode,
|
||||
}
|
||||
}
|
||||
return n.curr
|
||||
}
|
||||
|
||||
// Find searches the Node that matches by the specified XPath expr.
|
||||
func Find(top *Node, expr string) []*Node {
|
||||
exp, err := xpath.Compile(expr)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
t := exp.Select(CreateXPathNavigator(top))
|
||||
var elems []*Node
|
||||
for t.MoveNext() {
|
||||
elems = append(elems, getCurrentNode(t))
|
||||
}
|
||||
return elems
|
||||
}
|
||||
|
||||
// FindOne searches the Node that matches by the specified XPath expr,
|
||||
// and returns first element of matched.
|
||||
func FindOne(top *Node, expr string) *Node {
|
||||
exp, err := xpath.Compile(expr)
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
t := exp.Select(CreateXPathNavigator(top))
|
||||
var elem *Node
|
||||
if t.MoveNext() {
|
||||
elem = getCurrentNode(t)
|
||||
}
|
||||
return elem
|
||||
}
|
||||
|
||||
// FindEach searches the html.Node and calls functions cb.
|
||||
// Important: this method has deprecated, recommend use for .. = range Find(){}.
|
||||
func FindEach(top *Node, expr string, cb func(int, *Node)) {
|
||||
for i, n := range Find(top, expr) {
|
||||
cb(i, n)
|
||||
}
|
||||
}
|
||||
|
||||
// FindEachWithBreak functions the same as FindEach but allows you
|
||||
// to break the loop by returning false from your callback function, cb.
|
||||
// Important: this method has deprecated, recommend use for .. = range Find(){}.
|
||||
func FindEachWithBreak(top *Node, expr string, cb func(int, *Node) bool) {
|
||||
for i, n := range Find(top, expr) {
|
||||
if !cb(i, n) {
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
type NodeNavigator struct {
|
||||
root, curr *Node
|
||||
attr int
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) Current() *Node {
|
||||
return x.curr
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) NodeType() xpath.NodeType {
|
||||
switch x.curr.Type {
|
||||
case CommentNode:
|
||||
return xpath.CommentNode
|
||||
case TextNode:
|
||||
return xpath.TextNode
|
||||
case DeclarationNode, DocumentNode:
|
||||
return xpath.RootNode
|
||||
case ElementNode:
|
||||
if x.attr != -1 {
|
||||
return xpath.AttributeNode
|
||||
}
|
||||
return xpath.ElementNode
|
||||
}
|
||||
panic(fmt.Sprintf("unknown XML node type: %v", x.curr.Type))
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) LocalName() string {
|
||||
if x.attr != -1 {
|
||||
return x.curr.Attr[x.attr].Name.Local
|
||||
}
|
||||
return x.curr.Data
|
||||
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) Prefix() string {
|
||||
if x.NodeType() == xpath.AttributeNode {
|
||||
if x.attr != -1 {
|
||||
return x.curr.Attr[x.attr].Name.Space
|
||||
}
|
||||
return ""
|
||||
}
|
||||
return x.curr.Prefix
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) Value() string {
|
||||
switch x.curr.Type {
|
||||
case CommentNode:
|
||||
return x.curr.Data
|
||||
case ElementNode:
|
||||
if x.attr != -1 {
|
||||
return x.curr.Attr[x.attr].Value
|
||||
}
|
||||
return x.curr.InnerText()
|
||||
case TextNode:
|
||||
return x.curr.Data
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) Copy() xpath.NodeNavigator {
|
||||
n := *x
|
||||
return &n
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) MoveToRoot() {
|
||||
x.curr = x.root
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) MoveToParent() bool {
|
||||
if x.attr != -1 {
|
||||
x.attr = -1
|
||||
return true
|
||||
} else if node := x.curr.Parent; node != nil {
|
||||
x.curr = node
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) MoveToNextAttribute() bool {
|
||||
if x.attr >= len(x.curr.Attr)-1 {
|
||||
return false
|
||||
}
|
||||
x.attr++
|
||||
return true
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) MoveToChild() bool {
|
||||
if x.attr != -1 {
|
||||
return false
|
||||
}
|
||||
if node := x.curr.FirstChild; node != nil {
|
||||
x.curr = node
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) MoveToFirst() bool {
|
||||
if x.attr != -1 || x.curr.PrevSibling == nil {
|
||||
return false
|
||||
}
|
||||
for {
|
||||
node := x.curr.PrevSibling
|
||||
if node == nil {
|
||||
break
|
||||
}
|
||||
x.curr = node
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) String() string {
|
||||
return x.Value()
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) MoveToNext() bool {
|
||||
if x.attr != -1 {
|
||||
return false
|
||||
}
|
||||
if node := x.curr.NextSibling; node != nil {
|
||||
x.curr = node
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) MoveToPrevious() bool {
|
||||
if x.attr != -1 {
|
||||
return false
|
||||
}
|
||||
if node := x.curr.PrevSibling; node != nil {
|
||||
x.curr = node
|
||||
return true
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func (x *NodeNavigator) MoveTo(other xpath.NodeNavigator) bool {
|
||||
node, ok := other.(*NodeNavigator)
|
||||
if !ok || node.root != x.root {
|
||||
return false
|
||||
}
|
||||
|
||||
x.curr = node.curr
|
||||
x.attr = node.attr
|
||||
return true
|
||||
}
|
||||
|
|
@ -1 +0,0 @@
|
|||
comment: false
|
||||
|
|
@ -1,17 +0,0 @@
|
|||
language: go
|
||||
sudo: false
|
||||
go:
|
||||
- 1.9.x
|
||||
- 1.10.x
|
||||
- 1.11.x
|
||||
- tip
|
||||
script:
|
||||
- go get -u golang.org/x/lint/golint
|
||||
- OUT="$(go get -a)"; test -z "$OUT" || (echo "$OUT" && return 1)
|
||||
- OUT="$(gofmt -l -d ./)"; test -z "$OUT" || (echo "$OUT" && return 1)
|
||||
- OUT="$(golint ./...)"; test -z "$OUT" || (echo "$OUT" && return 1)
|
||||
- go vet -v ./...
|
||||
- go test -race -v -coverprofile=coverage.txt -covermode=atomic ./
|
||||
- go build
|
||||
after_success:
|
||||
- bash <(curl -s https://codecov.io/bash)
|
||||
|
|
@ -1,23 +0,0 @@
|
|||
# 1.2.0 - 2019.02.13
|
||||
|
||||
- Compatibility with the latest htmlquery package
|
||||
- New request shortcut for HEAD requests
|
||||
- Check URL availibility before visiting
|
||||
- Fix proxy URL value
|
||||
- Request counter fix
|
||||
- Minor fixes in examples
|
||||
|
||||
# 1.1.0 - 2018.08.13
|
||||
|
||||
- Appengine integration takes context.Context instead of http.Request (API change)
|
||||
- Added "Accept" http header by default to every request
|
||||
- Support slices of pointers in unmarshal
|
||||
- Fixed a race condition in queues
|
||||
- ForEachWithBreak method added to HTMLElement
|
||||
- Added a local file example
|
||||
- Support gzip decompression of response bodies
|
||||
- Don't share waitgroup when cloning a collector
|
||||
- Fixed instagram example
|
||||
|
||||
|
||||
# 1.0.0 - 2018.05.13
|
||||
|
|
@ -1,67 +0,0 @@
|
|||
# Contribute
|
||||
|
||||
## Introduction
|
||||
|
||||
First, thank you for considering contributing to colly! It's people like you that make the open source community such a great community! 😊
|
||||
|
||||
We welcome any type of contribution, not only code. You can help with
|
||||
- **QA**: file bug reports, the more details you can give the better (e.g. screenshots with the console open)
|
||||
- **Marketing**: writing blog posts, howto's, printing stickers, ...
|
||||
- **Community**: presenting the project at meetups, organizing a dedicated meetup for the local community, ...
|
||||
- **Code**: take a look at the [open issues](https://github.com/gocolly/colly/issues). Even if you can't write code, commenting on them, showing that you care about a given issue matters. It helps us triage them.
|
||||
- **Money**: we welcome financial contributions in full transparency on our [open collective](https://opencollective.com/colly).
|
||||
|
||||
## Your First Contribution
|
||||
|
||||
Working on your first Pull Request? You can learn how from this *free* series, [How to Contribute to an Open Source Project on GitHub](https://egghead.io/series/how-to-contribute-to-an-open-source-project-on-github).
|
||||
|
||||
## Submitting code
|
||||
|
||||
Any code change should be submitted as a pull request. The description should explain what the code does and give steps to execute it. The pull request should also contain tests.
|
||||
|
||||
## Code review process
|
||||
|
||||
The bigger the pull request, the longer it will take to review and merge. Try to break down large pull requests in smaller chunks that are easier to review and merge.
|
||||
It is also always helpful to have some context for your pull request. What was the purpose? Why does it matter to you?
|
||||
|
||||
## Financial contributions
|
||||
|
||||
We also welcome financial contributions in full transparency on our [open collective](https://opencollective.com/colly).
|
||||
Anyone can file an expense. If the expense makes sense for the development of the community, it will be "merged" in the ledger of our open collective by the core contributors and the person who filed the expense will be reimbursed.
|
||||
|
||||
## Questions
|
||||
|
||||
If you have any questions, create an [issue](https://github.com/gocolly/colly/issues/new) (protip: do a quick search first to see if someone else didn't ask the same question before!).
|
||||
You can also reach us at hello@colly.opencollective.com.
|
||||
|
||||
## Credits
|
||||
|
||||
### Contributors
|
||||
|
||||
Thank you to all the people who have already contributed to colly!
|
||||
<a href="graphs/contributors"><img src="https://opencollective.com/colly/contributors.svg?width=890" /></a>
|
||||
|
||||
|
||||
### Backers
|
||||
|
||||
Thank you to all our backers! [[Become a backer](https://opencollective.com/colly#backer)]
|
||||
|
||||
<a href="https://opencollective.com/colly#backers" target="_blank"><img src="https://opencollective.com/colly/backers.svg?width=890"></a>
|
||||
|
||||
|
||||
### Sponsors
|
||||
|
||||
Thank you to all our sponsors! (please ask your company to also support this open source project by [becoming a sponsor](https://opencollective.com/colly#sponsor))
|
||||
|
||||
<a href="https://opencollective.com/colly/sponsor/0/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/0/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/1/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/1/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/2/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/2/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/3/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/3/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/4/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/4/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/5/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/5/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/6/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/6/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/7/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/7/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/8/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/8/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/9/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/9/avatar.svg"></a>
|
||||
|
||||
<!-- This `CONTRIBUTING.md` is based on @nayafia's template https://github.com/nayafia/contributing-template -->
|
||||
|
|
@ -1,202 +0,0 @@
|
|||
|
||||
Apache License
|
||||
Version 2.0, January 2004
|
||||
http://www.apache.org/licenses/
|
||||
|
||||
TERMS AND CONDITIONS FOR USE, REPRODUCTION, AND DISTRIBUTION
|
||||
|
||||
1. Definitions.
|
||||
|
||||
"License" shall mean the terms and conditions for use, reproduction,
|
||||
and distribution as defined by Sections 1 through 9 of this document.
|
||||
|
||||
"Licensor" shall mean the copyright owner or entity authorized by
|
||||
the copyright owner that is granting the License.
|
||||
|
||||
"Legal Entity" shall mean the union of the acting entity and all
|
||||
other entities that control, are controlled by, or are under common
|
||||
control with that entity. For the purposes of this definition,
|
||||
"control" means (i) the power, direct or indirect, to cause the
|
||||
direction or management of such entity, whether by contract or
|
||||
otherwise, or (ii) ownership of fifty percent (50%) or more of the
|
||||
outstanding shares, or (iii) beneficial ownership of such entity.
|
||||
|
||||
"You" (or "Your") shall mean an individual or Legal Entity
|
||||
exercising permissions granted by this License.
|
||||
|
||||
"Source" form shall mean the preferred form for making modifications,
|
||||
including but not limited to software source code, documentation
|
||||
source, and configuration files.
|
||||
|
||||
"Object" form shall mean any form resulting from mechanical
|
||||
transformation or translation of a Source form, including but
|
||||
not limited to compiled object code, generated documentation,
|
||||
and conversions to other media types.
|
||||
|
||||
"Work" shall mean the work of authorship, whether in Source or
|
||||
Object form, made available under the License, as indicated by a
|
||||
copyright notice that is included in or attached to the work
|
||||
(an example is provided in the Appendix below).
|
||||
|
||||
"Derivative Works" shall mean any work, whether in Source or Object
|
||||
form, that is based on (or derived from) the Work and for which the
|
||||
editorial revisions, annotations, elaborations, or other modifications
|
||||
represent, as a whole, an original work of authorship. For the purposes
|
||||
of this License, Derivative Works shall not include works that remain
|
||||
separable from, or merely link (or bind by name) to the interfaces of,
|
||||
the Work and Derivative Works thereof.
|
||||
|
||||
"Contribution" shall mean any work of authorship, including
|
||||
the original version of the Work and any modifications or additions
|
||||
to that Work or Derivative Works thereof, that is intentionally
|
||||
submitted to Licensor for inclusion in the Work by the copyright owner
|
||||
or by an individual or Legal Entity authorized to submit on behalf of
|
||||
the copyright owner. For the purposes of this definition, "submitted"
|
||||
means any form of electronic, verbal, or written communication sent
|
||||
to the Licensor or its representatives, including but not limited to
|
||||
communication on electronic mailing lists, source code control systems,
|
||||
and issue tracking systems that are managed by, or on behalf of, the
|
||||
Licensor for the purpose of discussing and improving the Work, but
|
||||
excluding communication that is conspicuously marked or otherwise
|
||||
designated in writing by the copyright owner as "Not a Contribution."
|
||||
|
||||
"Contributor" shall mean Licensor and any individual or Legal Entity
|
||||
on behalf of whom a Contribution has been received by Licensor and
|
||||
subsequently incorporated within the Work.
|
||||
|
||||
2. Grant of Copyright License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
copyright license to reproduce, prepare Derivative Works of,
|
||||
publicly display, publicly perform, sublicense, and distribute the
|
||||
Work and such Derivative Works in Source or Object form.
|
||||
|
||||
3. Grant of Patent License. Subject to the terms and conditions of
|
||||
this License, each Contributor hereby grants to You a perpetual,
|
||||
worldwide, non-exclusive, no-charge, royalty-free, irrevocable
|
||||
(except as stated in this section) patent license to make, have made,
|
||||
use, offer to sell, sell, import, and otherwise transfer the Work,
|
||||
where such license applies only to those patent claims licensable
|
||||
by such Contributor that are necessarily infringed by their
|
||||
Contribution(s) alone or by combination of their Contribution(s)
|
||||
with the Work to which such Contribution(s) was submitted. If You
|
||||
institute patent litigation against any entity (including a
|
||||
cross-claim or counterclaim in a lawsuit) alleging that the Work
|
||||
or a Contribution incorporated within the Work constitutes direct
|
||||
or contributory patent infringement, then any patent licenses
|
||||
granted to You under this License for that Work shall terminate
|
||||
as of the date such litigation is filed.
|
||||
|
||||
4. Redistribution. You may reproduce and distribute copies of the
|
||||
Work or Derivative Works thereof in any medium, with or without
|
||||
modifications, and in Source or Object form, provided that You
|
||||
meet the following conditions:
|
||||
|
||||
(a) You must give any other recipients of the Work or
|
||||
Derivative Works a copy of this License; and
|
||||
|
||||
(b) You must cause any modified files to carry prominent notices
|
||||
stating that You changed the files; and
|
||||
|
||||
(c) You must retain, in the Source form of any Derivative Works
|
||||
that You distribute, all copyright, patent, trademark, and
|
||||
attribution notices from the Source form of the Work,
|
||||
excluding those notices that do not pertain to any part of
|
||||
the Derivative Works; and
|
||||
|
||||
(d) If the Work includes a "NOTICE" text file as part of its
|
||||
distribution, then any Derivative Works that You distribute must
|
||||
include a readable copy of the attribution notices contained
|
||||
within such NOTICE file, excluding those notices that do not
|
||||
pertain to any part of the Derivative Works, in at least one
|
||||
of the following places: within a NOTICE text file distributed
|
||||
as part of the Derivative Works; within the Source form or
|
||||
documentation, if provided along with the Derivative Works; or,
|
||||
within a display generated by the Derivative Works, if and
|
||||
wherever such third-party notices normally appear. The contents
|
||||
of the NOTICE file are for informational purposes only and
|
||||
do not modify the License. You may add Your own attribution
|
||||
notices within Derivative Works that You distribute, alongside
|
||||
or as an addendum to the NOTICE text from the Work, provided
|
||||
that such additional attribution notices cannot be construed
|
||||
as modifying the License.
|
||||
|
||||
You may add Your own copyright statement to Your modifications and
|
||||
may provide additional or different license terms and conditions
|
||||
for use, reproduction, or distribution of Your modifications, or
|
||||
for any such Derivative Works as a whole, provided Your use,
|
||||
reproduction, and distribution of the Work otherwise complies with
|
||||
the conditions stated in this License.
|
||||
|
||||
5. Submission of Contributions. Unless You explicitly state otherwise,
|
||||
any Contribution intentionally submitted for inclusion in the Work
|
||||
by You to the Licensor shall be under the terms and conditions of
|
||||
this License, without any additional terms or conditions.
|
||||
Notwithstanding the above, nothing herein shall supersede or modify
|
||||
the terms of any separate license agreement you may have executed
|
||||
with Licensor regarding such Contributions.
|
||||
|
||||
6. Trademarks. This License does not grant permission to use the trade
|
||||
names, trademarks, service marks, or product names of the Licensor,
|
||||
except as required for reasonable and customary use in describing the
|
||||
origin of the Work and reproducing the content of the NOTICE file.
|
||||
|
||||
7. Disclaimer of Warranty. Unless required by applicable law or
|
||||
agreed to in writing, Licensor provides the Work (and each
|
||||
Contributor provides its Contributions) on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or
|
||||
implied, including, without limitation, any warranties or conditions
|
||||
of TITLE, NON-INFRINGEMENT, MERCHANTABILITY, or FITNESS FOR A
|
||||
PARTICULAR PURPOSE. You are solely responsible for determining the
|
||||
appropriateness of using or redistributing the Work and assume any
|
||||
risks associated with Your exercise of permissions under this License.
|
||||
|
||||
8. Limitation of Liability. In no event and under no legal theory,
|
||||
whether in tort (including negligence), contract, or otherwise,
|
||||
unless required by applicable law (such as deliberate and grossly
|
||||
negligent acts) or agreed to in writing, shall any Contributor be
|
||||
liable to You for damages, including any direct, indirect, special,
|
||||
incidental, or consequential damages of any character arising as a
|
||||
result of this License or out of the use or inability to use the
|
||||
Work (including but not limited to damages for loss of goodwill,
|
||||
work stoppage, computer failure or malfunction, or any and all
|
||||
other commercial damages or losses), even if such Contributor
|
||||
has been advised of the possibility of such damages.
|
||||
|
||||
9. Accepting Warranty or Additional Liability. While redistributing
|
||||
the Work or Derivative Works thereof, You may choose to offer,
|
||||
and charge a fee for, acceptance of support, warranty, indemnity,
|
||||
or other liability obligations and/or rights consistent with this
|
||||
License. However, in accepting such obligations, You may act only
|
||||
on Your own behalf and on Your sole responsibility, not on behalf
|
||||
of any other Contributor, and only if You agree to indemnify,
|
||||
defend, and hold each Contributor harmless for any liability
|
||||
incurred by, or claims asserted against, such Contributor by reason
|
||||
of your accepting any such warranty or additional liability.
|
||||
|
||||
END OF TERMS AND CONDITIONS
|
||||
|
||||
APPENDIX: How to apply the Apache License to your work.
|
||||
|
||||
To apply the Apache License to your work, attach the following
|
||||
boilerplate notice, with the fields enclosed by brackets "[]"
|
||||
replaced with your own identifying information. (Don't include
|
||||
the brackets!) The text should be enclosed in the appropriate
|
||||
comment syntax for the file format. We also recommend that a
|
||||
file or class name and description of purpose be included on the
|
||||
same "printed page" as the copyright notice for easier
|
||||
identification within third-party archives.
|
||||
|
||||
Copyright [yyyy] [name of copyright owner]
|
||||
|
||||
Licensed under the Apache License, Version 2.0 (the "License");
|
||||
you may not use this file except in compliance with the License.
|
||||
You may obtain a copy of the License at
|
||||
|
||||
http://www.apache.org/licenses/LICENSE-2.0
|
||||
|
||||
Unless required by applicable law or agreed to in writing, software
|
||||
distributed under the License is distributed on an "AS IS" BASIS,
|
||||
WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
See the License for the specific language governing permissions and
|
||||
limitations under the License.
|
||||
|
|
@ -1,112 +0,0 @@
|
|||
# Colly
|
||||
|
||||
Lightning Fast and Elegant Scraping Framework for Gophers
|
||||
|
||||
Colly provides a clean interface to write any kind of crawler/scraper/spider.
|
||||
|
||||
With Colly you can easily extract structured data from websites, which can be used for a wide range of applications, like data mining, data processing or archiving.
|
||||
|
||||
[](https://godoc.org/github.com/gocolly/colly)
|
||||
[](#backers) [](#sponsors) [](https://travis-ci.org/gocolly/colly)
|
||||
[](http://goreportcard.com/report/gocolly/colly)
|
||||
[](https://github.com/gocolly/colly/tree/master/_examples)
|
||||
[](https://codecov.io/github/gocolly/colly?branch=master)
|
||||
[](https://app.fossa.io/projects/git%2Bgithub.com%2Fgocolly%2Fcolly?ref=badge_shield)
|
||||
[](https://twitter.com/gocolly)
|
||||
|
||||
|
||||
## Features
|
||||
|
||||
* Clean API
|
||||
* Fast (>1k request/sec on a single core)
|
||||
* Manages request delays and maximum concurrency per domain
|
||||
* Automatic cookie and session handling
|
||||
* Sync/async/parallel scraping
|
||||
* Caching
|
||||
* Automatic encoding of non-unicode responses
|
||||
* Robots.txt support
|
||||
* Distributed scraping
|
||||
* Configuration via environment variables
|
||||
* Extensions
|
||||
|
||||
|
||||
## Example
|
||||
|
||||
```go
|
||||
func main() {
|
||||
c := colly.NewCollector()
|
||||
|
||||
// Find and visit all links
|
||||
c.OnHTML("a[href]", func(e *colly.HTMLElement) {
|
||||
e.Request.Visit(e.Attr("href"))
|
||||
})
|
||||
|
||||
c.OnRequest(func(r *colly.Request) {
|
||||
fmt.Println("Visiting", r.URL)
|
||||
})
|
||||
|
||||
c.Visit("http://go-colly.org/")
|
||||
}
|
||||
```
|
||||
|
||||
See [examples folder](https://github.com/gocolly/colly/tree/master/_examples) for more detailed examples.
|
||||
|
||||
|
||||
## Installation
|
||||
|
||||
```
|
||||
go get -u github.com/gocolly/colly/...
|
||||
```
|
||||
|
||||
|
||||
## Bugs
|
||||
|
||||
Bugs or suggestions? Visit the [issue tracker](https://github.com/gocolly/colly/issues) or join `#colly` on freenode
|
||||
|
||||
|
||||
## Other Projects Using Colly
|
||||
|
||||
Below is a list of public, open source projects that use Colly:
|
||||
|
||||
* [greenpeace/check-my-pages](https://github.com/greenpeace/check-my-pages) Scraping script to test the Spanish Greenpeace web archive
|
||||
* [altsab/gowap](https://github.com/altsab/gowap) Wappalyzer implementation in Go
|
||||
* [jesuiscamille/goquotes](https://github.com/jesuiscamille/goquotes) A quotes scrapper, making your day a little better!
|
||||
* [jivesearch/jivesearch](https://github.com/jivesearch/jivesearch) A search engine that doesn't track you.
|
||||
* [Leagify/colly-draft-prospects](https://github.com/Leagify/colly-draft-prospects) A scraper for future NFL Draft prospects.
|
||||
* [lucasepe/go-ps4](https://github.com/lucasepe/go-ps4) Search playstation store for your favorite PS4 games using the command line.
|
||||
|
||||
If you are using Colly in a project please send a pull request to add it to the list.
|
||||
|
||||
## Contributors
|
||||
|
||||
This project exists thanks to all the people who contribute. [[Contribute]](CONTRIBUTING.md).
|
||||
<a href="https://github.com/gocolly/colly/graphs/contributors"><img src="https://opencollective.com/colly/contributors.svg?width=890" /></a>
|
||||
|
||||
|
||||
## Backers
|
||||
|
||||
Thank you to all our backers! 🙏 [[Become a backer](https://opencollective.com/colly#backer)]
|
||||
|
||||
<a href="https://opencollective.com/colly#backers" target="_blank"><img src="https://opencollective.com/colly/backers.svg?width=890"></a>
|
||||
|
||||
|
||||
## Sponsors
|
||||
|
||||
Support this project by becoming a sponsor. Your logo will show up here with a link to your website. [[Become a sponsor](https://opencollective.com/colly#sponsor)]
|
||||
|
||||
<a href="https://opencollective.com/colly/sponsor/0/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/0/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/1/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/1/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/2/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/2/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/3/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/3/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/4/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/4/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/5/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/5/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/6/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/6/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/7/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/7/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/8/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/8/avatar.svg"></a>
|
||||
<a href="https://opencollective.com/colly/sponsor/9/website" target="_blank"><img src="https://opencollective.com/colly/sponsor/9/avatar.svg"></a>
|
||||
|
||||
|
||||
|
||||
|
||||
## License
|
||||
[](https://app.fossa.io/projects/git%2Bgithub.com%2Fgocolly%2Fcolly?ref=badge_large)
|
||||
|
|
@ -1 +0,0 @@
|
|||
1.2.0
|
||||
File diff suppressed because it is too large
Load Diff
|
|
@ -1,87 +0,0 @@
|
|||
// Copyright 2018 Adam Tauber
|
||||
//
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
package colly
|
||||
|
||||
import (
|
||||
"sync"
|
||||
)
|
||||
|
||||
// Context provides a tiny layer for passing data between callbacks
|
||||
type Context struct {
|
||||
contextMap map[string]interface{}
|
||||
lock *sync.RWMutex
|
||||
}
|
||||
|
||||
// NewContext initializes a new Context instance
|
||||
func NewContext() *Context {
|
||||
return &Context{
|
||||
contextMap: make(map[string]interface{}),
|
||||
lock: &sync.RWMutex{},
|
||||
}
|
||||
}
|
||||
|
||||
// UnmarshalBinary decodes Context value to nil
|
||||
// This function is used by request caching
|
||||
func (c *Context) UnmarshalBinary(_ []byte) error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// MarshalBinary encodes Context value
|
||||
// This function is used by request caching
|
||||
func (c *Context) MarshalBinary() (_ []byte, _ error) {
|
||||
return nil, nil
|
||||
}
|
||||
|
||||
// Put stores a value of any type in Context
|
||||
func (c *Context) Put(key string, value interface{}) {
|
||||
c.lock.Lock()
|
||||
c.contextMap[key] = value
|
||||
c.lock.Unlock()
|
||||
}
|
||||
|
||||
// Get retrieves a string value from Context.
|
||||
// Get returns an empty string if key not found
|
||||
func (c *Context) Get(key string) string {
|
||||
c.lock.RLock()
|
||||
defer c.lock.RUnlock()
|
||||
if v, ok := c.contextMap[key]; ok {
|
||||
return v.(string)
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// GetAny retrieves a value from Context.
|
||||
// GetAny returns nil if key not found
|
||||
func (c *Context) GetAny(key string) interface{} {
|
||||
c.lock.RLock()
|
||||
defer c.lock.RUnlock()
|
||||
if v, ok := c.contextMap[key]; ok {
|
||||
return v
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// ForEach iterate context
|
||||
func (c *Context) ForEach(fn func(k string, v interface{}) interface{}) []interface{} {
|
||||
c.lock.RLock()
|
||||
defer c.lock.RUnlock()
|
||||
|
||||
ret := make([]interface{}, 0, len(c.contextMap))
|
||||
for k, v := range c.contextMap {
|
||||
ret = append(ret, fn(k, v))
|
||||
}
|
||||
|
||||
return ret
|
||||
}
|
||||
|
|
@ -1,36 +0,0 @@
|
|||
// Copyright 2018 Adam Tauber
|
||||
//
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
package debug
|
||||
|
||||
// Event represents an action inside a collector
|
||||
type Event struct {
|
||||
// Type is the type of the event
|
||||
Type string
|
||||
// RequestID identifies the HTTP request of the Event
|
||||
RequestID uint32
|
||||
// CollectorID identifies the collector of the Event
|
||||
CollectorID uint32
|
||||
// Values contains the event's key-value pairs. Different type of events
|
||||
// can return different key-value pairs
|
||||
Values map[string]string
|
||||
}
|
||||
|
||||
// Debugger is an interface for different type of debugging backends
|
||||
type Debugger interface {
|
||||
// Init initializes the backend
|
||||
Init() error
|
||||
// Event receives a new collector event.
|
||||
Event(e *Event)
|
||||
}
|
||||
|
|
@ -1,54 +0,0 @@
|
|||
// Copyright 2018 Adam Tauber
|
||||
//
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
package debug
|
||||
|
||||
import (
|
||||
"io"
|
||||
"log"
|
||||
"os"
|
||||
"sync/atomic"
|
||||
"time"
|
||||
)
|
||||
|
||||
// LogDebugger is the simplest debugger which prints log messages to the STDERR
|
||||
type LogDebugger struct {
|
||||
// Output is the log destination, anything can be used which implements them
|
||||
// io.Writer interface. Leave it blank to use STDERR
|
||||
Output io.Writer
|
||||
// Prefix appears at the beginning of each generated log line
|
||||
Prefix string
|
||||
// Flag defines the logging properties.
|
||||
Flag int
|
||||
logger *log.Logger
|
||||
counter int32
|
||||
start time.Time
|
||||
}
|
||||
|
||||
// Init initializes the LogDebugger
|
||||
func (l *LogDebugger) Init() error {
|
||||
l.counter = 0
|
||||
l.start = time.Now()
|
||||
if l.Output == nil {
|
||||
l.Output = os.Stderr
|
||||
}
|
||||
l.logger = log.New(l.Output, l.Prefix, l.Flag)
|
||||
return nil
|
||||
}
|
||||
|
||||
// Event receives Collector events and prints them to STDERR
|
||||
func (l *LogDebugger) Event(e *Event) {
|
||||
i := atomic.AddInt32(&l.counter, 1)
|
||||
l.logger.Printf("[%06d] %d [%6d - %s] %q (%s)\n", i, e.CollectorID, e.RequestID, e.Type, e.Values, time.Since(l.start))
|
||||
}
|
||||
|
|
@ -1,146 +0,0 @@
|
|||
// Copyright 2018 Adam Tauber
|
||||
//
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
package debug
|
||||
|
||||
import (
|
||||
"encoding/json"
|
||||
"log"
|
||||
"net/http"
|
||||
"time"
|
||||
)
|
||||
|
||||
// WebDebugger is a web based debuging frontend for colly
|
||||
type WebDebugger struct {
|
||||
// Address is the address of the web server. It is 127.0.0.1:7676 by default.
|
||||
Address string
|
||||
initialized bool
|
||||
CurrentRequests map[uint32]requestInfo
|
||||
RequestLog []requestInfo
|
||||
}
|
||||
|
||||
type requestInfo struct {
|
||||
URL string
|
||||
Started time.Time
|
||||
Duration time.Duration
|
||||
ResponseStatus string
|
||||
ID uint32
|
||||
CollectorID uint32
|
||||
}
|
||||
|
||||
// Init initializes the WebDebugger
|
||||
func (w *WebDebugger) Init() error {
|
||||
if w.initialized {
|
||||
return nil
|
||||
}
|
||||
defer func() {
|
||||
w.initialized = true
|
||||
}()
|
||||
if w.Address == "" {
|
||||
w.Address = "127.0.0.1:7676"
|
||||
}
|
||||
w.RequestLog = make([]requestInfo, 0)
|
||||
w.CurrentRequests = make(map[uint32]requestInfo)
|
||||
http.HandleFunc("/", w.indexHandler)
|
||||
http.HandleFunc("/status", w.statusHandler)
|
||||
log.Println("Starting debug webserver on", w.Address)
|
||||
go http.ListenAndServe(w.Address, nil)
|
||||
return nil
|
||||
}
|
||||
|
||||
// Event updates the debugger's status
|
||||
func (w *WebDebugger) Event(e *Event) {
|
||||
switch e.Type {
|
||||
case "request":
|
||||
w.CurrentRequests[e.RequestID] = requestInfo{
|
||||
URL: e.Values["url"],
|
||||
Started: time.Now(),
|
||||
ID: e.RequestID,
|
||||
CollectorID: e.CollectorID,
|
||||
}
|
||||
case "response", "error":
|
||||
r := w.CurrentRequests[e.RequestID]
|
||||
r.Duration = time.Since(r.Started)
|
||||
r.ResponseStatus = e.Values["status"]
|
||||
w.RequestLog = append(w.RequestLog, r)
|
||||
delete(w.CurrentRequests, e.RequestID)
|
||||
}
|
||||
}
|
||||
|
||||
func (w *WebDebugger) indexHandler(wr http.ResponseWriter, r *http.Request) {
|
||||
wr.Write([]byte(`<!DOCTYPE html>
|
||||
<html>
|
||||
<head>
|
||||
<title>Colly Debugger WebUI</title>
|
||||
<script src="https://code.jquery.com/jquery-latest.min.js" type="text/javascript"></script>
|
||||
<link rel="stylesheet" type="text/css" href="https://semantic-ui.com/dist/semantic.min.css">
|
||||
</head>
|
||||
<body>
|
||||
<div class="ui inverted vertical masthead center aligned segment" id="menu">
|
||||
<div class="ui tiny secondary inverted menu">
|
||||
<a class="item" href="/"><b>Colly WebDebugger</b></a>
|
||||
</div>
|
||||
</div>
|
||||
<div class="ui grid container">
|
||||
<div class="row">
|
||||
<div class="eight wide column">
|
||||
<h1>Current Requests <span id="current_request_count"></span></h1>
|
||||
<div id="current_requests" class="ui small feed"></div>
|
||||
</div>
|
||||
<div class="eight wide column">
|
||||
<h1>Finished Requests <span id="request_log_count"></span></h1>
|
||||
<div id="request_log" class="ui small feed"></div>
|
||||
</div>
|
||||
</div>
|
||||
</div>
|
||||
<script>
|
||||
function curRequestTpl(url, started, collectorId) {
|
||||
return '<div class="event"><div class="content"><div class="summary">' + url + '</div><div class="meta">Collector #' + collectorId + ' - ' + started + "</div></div></div>";
|
||||
}
|
||||
function requestLogTpl(url, duration, collectorId) {
|
||||
return '<div class="event"><div class="content"><div class="summary">' + url + '</div><div class="meta">Collector #' + collectorId + ' - ' + (duration/1000000000) + "s</div></div></div>";
|
||||
}
|
||||
function fetchStatus() {
|
||||
$.getJSON("/status", function(data) {
|
||||
$("#current_requests").html("");
|
||||
$("#request_log").html("");
|
||||
$("#current_request_count").text('(' + Object.keys(data.CurrentRequests).length + ')');
|
||||
$("#request_log_count").text('(' + data.RequestLog.length + ')');
|
||||
for(var i in data.CurrentRequests) {
|
||||
var r = data.CurrentRequests[i];
|
||||
$("#current_requests").append(curRequestTpl(r.Url, r.Started, r.CollectorId));
|
||||
}
|
||||
for(var i in data.RequestLog.reverse()) {
|
||||
var r = data.RequestLog[i];
|
||||
$("#request_log").append(requestLogTpl(r.Url, r.Duration, r.CollectorId));
|
||||
}
|
||||
setTimeout(fetchStatus, 1000);
|
||||
});
|
||||
}
|
||||
$(document).ready(function() {
|
||||
fetchStatus();
|
||||
});
|
||||
</script>
|
||||
</body>
|
||||
</html>
|
||||
`))
|
||||
}
|
||||
|
||||
func (w *WebDebugger) statusHandler(wr http.ResponseWriter, r *http.Request) {
|
||||
jsonData, err := json.MarshalIndent(w, "", " ")
|
||||
if err != nil {
|
||||
panic(err)
|
||||
}
|
||||
wr.Write(jsonData)
|
||||
}
|
||||
|
|
@ -1,120 +0,0 @@
|
|||
// Copyright 2018 Adam Tauber
|
||||
//
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
package colly
|
||||
|
||||
import (
|
||||
"strings"
|
||||
|
||||
"github.com/PuerkitoBio/goquery"
|
||||
"golang.org/x/net/html"
|
||||
)
|
||||
|
||||
// HTMLElement is the representation of a HTML tag.
|
||||
type HTMLElement struct {
|
||||
// Name is the name of the tag
|
||||
Name string
|
||||
Text string
|
||||
attributes []html.Attribute
|
||||
// Request is the request object of the element's HTML document
|
||||
Request *Request
|
||||
// Response is the Response object of the element's HTML document
|
||||
Response *Response
|
||||
// DOM is the goquery parsed DOM object of the page. DOM is relative
|
||||
// to the current HTMLElement
|
||||
DOM *goquery.Selection
|
||||
// Index stores the position of the current element within all the elements matched by an OnHTML callback
|
||||
Index int
|
||||
}
|
||||
|
||||
// NewHTMLElementFromSelectionNode creates a HTMLElement from a goquery.Selection Node.
|
||||
func NewHTMLElementFromSelectionNode(resp *Response, s *goquery.Selection, n *html.Node, idx int) *HTMLElement {
|
||||
return &HTMLElement{
|
||||
Name: n.Data,
|
||||
Request: resp.Request,
|
||||
Response: resp,
|
||||
Text: goquery.NewDocumentFromNode(n).Text(),
|
||||
DOM: s,
|
||||
Index: idx,
|
||||
attributes: n.Attr,
|
||||
}
|
||||
}
|
||||
|
||||
// Attr returns the selected attribute of a HTMLElement or empty string
|
||||
// if no attribute found
|
||||
func (h *HTMLElement) Attr(k string) string {
|
||||
for _, a := range h.attributes {
|
||||
if a.Key == k {
|
||||
return a.Val
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// ChildText returns the concatenated and stripped text content of the matching
|
||||
// elements.
|
||||
func (h *HTMLElement) ChildText(goquerySelector string) string {
|
||||
return strings.TrimSpace(h.DOM.Find(goquerySelector).Text())
|
||||
}
|
||||
|
||||
// ChildAttr returns the stripped text content of the first matching
|
||||
// element's attribute.
|
||||
func (h *HTMLElement) ChildAttr(goquerySelector, attrName string) string {
|
||||
if attr, ok := h.DOM.Find(goquerySelector).Attr(attrName); ok {
|
||||
return strings.TrimSpace(attr)
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// ChildAttrs returns the stripped text content of all the matching
|
||||
// element's attributes.
|
||||
func (h *HTMLElement) ChildAttrs(goquerySelector, attrName string) []string {
|
||||
var res []string
|
||||
h.DOM.Find(goquerySelector).Each(func(_ int, s *goquery.Selection) {
|
||||
if attr, ok := s.Attr(attrName); ok {
|
||||
res = append(res, strings.TrimSpace(attr))
|
||||
}
|
||||
})
|
||||
return res
|
||||
}
|
||||
|
||||
// ForEach iterates over the elements matched by the first argument
|
||||
// and calls the callback function on every HTMLElement match.
|
||||
func (h *HTMLElement) ForEach(goquerySelector string, callback func(int, *HTMLElement)) {
|
||||
i := 0
|
||||
h.DOM.Find(goquerySelector).Each(func(_ int, s *goquery.Selection) {
|
||||
for _, n := range s.Nodes {
|
||||
callback(i, NewHTMLElementFromSelectionNode(h.Response, s, n, i))
|
||||
i++
|
||||
}
|
||||
})
|
||||
}
|
||||
|
||||
// ForEachWithBreak iterates over the elements matched by the first argument
|
||||
// and calls the callback function on every HTMLElement match.
|
||||
// It is identical to ForEach except that it is possible to break
|
||||
// out of the loop by returning false in the callback function. It returns the
|
||||
// current Selection object.
|
||||
func (h *HTMLElement) ForEachWithBreak(goquerySelector string, callback func(int, *HTMLElement) bool) {
|
||||
i := 0
|
||||
h.DOM.Find(goquerySelector).EachWithBreak(func(_ int, s *goquery.Selection) bool {
|
||||
for _, n := range s.Nodes {
|
||||
if callback(i, NewHTMLElementFromSelectionNode(h.Response, s, n, i)) {
|
||||
i++
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
})
|
||||
}
|
||||
|
|
@ -1,227 +0,0 @@
|
|||
// Copyright 2018 Adam Tauber
|
||||
//
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
package colly
|
||||
|
||||
import (
|
||||
"crypto/sha1"
|
||||
"encoding/gob"
|
||||
"encoding/hex"
|
||||
"io"
|
||||
"io/ioutil"
|
||||
"math/rand"
|
||||
"net/http"
|
||||
"os"
|
||||
"path"
|
||||
"regexp"
|
||||
"sync"
|
||||
"time"
|
||||
|
||||
"compress/gzip"
|
||||
|
||||
"github.com/gobwas/glob"
|
||||
)
|
||||
|
||||
type httpBackend struct {
|
||||
LimitRules []*LimitRule
|
||||
Client *http.Client
|
||||
lock *sync.RWMutex
|
||||
}
|
||||
|
||||
// LimitRule provides connection restrictions for domains.
|
||||
// Both DomainRegexp and DomainGlob can be used to specify
|
||||
// the included domains patterns, but at least one is required.
|
||||
// There can be two kind of limitations:
|
||||
// - Parallelism: Set limit for the number of concurrent requests to matching domains
|
||||
// - Delay: Wait specified amount of time between requests (parallelism is 1 in this case)
|
||||
type LimitRule struct {
|
||||
// DomainRegexp is a regular expression to match against domains
|
||||
DomainRegexp string
|
||||
// DomainRegexp is a glob pattern to match against domains
|
||||
DomainGlob string
|
||||
// Delay is the duration to wait before creating a new request to the matching domains
|
||||
Delay time.Duration
|
||||
// RandomDelay is the extra randomized duration to wait added to Delay before creating a new request
|
||||
RandomDelay time.Duration
|
||||
// Parallelism is the number of the maximum allowed concurrent requests of the matching domains
|
||||
Parallelism int
|
||||
waitChan chan bool
|
||||
compiledRegexp *regexp.Regexp
|
||||
compiledGlob glob.Glob
|
||||
}
|
||||
|
||||
// Init initializes the private members of LimitRule
|
||||
func (r *LimitRule) Init() error {
|
||||
waitChanSize := 1
|
||||
if r.Parallelism > 1 {
|
||||
waitChanSize = r.Parallelism
|
||||
}
|
||||
r.waitChan = make(chan bool, waitChanSize)
|
||||
hasPattern := false
|
||||
if r.DomainRegexp != "" {
|
||||
c, err := regexp.Compile(r.DomainRegexp)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
r.compiledRegexp = c
|
||||
hasPattern = true
|
||||
}
|
||||
if r.DomainGlob != "" {
|
||||
c, err := glob.Compile(r.DomainGlob)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
r.compiledGlob = c
|
||||
hasPattern = true
|
||||
}
|
||||
if !hasPattern {
|
||||
return ErrNoPattern
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func (h *httpBackend) Init(jar http.CookieJar) {
|
||||
rand.Seed(time.Now().UnixNano())
|
||||
h.Client = &http.Client{
|
||||
Jar: jar,
|
||||
Timeout: 10 * time.Second,
|
||||
}
|
||||
h.lock = &sync.RWMutex{}
|
||||
}
|
||||
|
||||
// Match checks that the domain parameter triggers the rule
|
||||
func (r *LimitRule) Match(domain string) bool {
|
||||
match := false
|
||||
if r.compiledRegexp != nil && r.compiledRegexp.MatchString(domain) {
|
||||
match = true
|
||||
}
|
||||
if r.compiledGlob != nil && r.compiledGlob.Match(domain) {
|
||||
match = true
|
||||
}
|
||||
return match
|
||||
}
|
||||
|
||||
func (h *httpBackend) GetMatchingRule(domain string) *LimitRule {
|
||||
if h.LimitRules == nil {
|
||||
return nil
|
||||
}
|
||||
h.lock.RLock()
|
||||
defer h.lock.RUnlock()
|
||||
for _, r := range h.LimitRules {
|
||||
if r.Match(domain) {
|
||||
return r
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func (h *httpBackend) Cache(request *http.Request, bodySize int, cacheDir string) (*Response, error) {
|
||||
if cacheDir == "" || request.Method != "GET" {
|
||||
return h.Do(request, bodySize)
|
||||
}
|
||||
sum := sha1.Sum([]byte(request.URL.String()))
|
||||
hash := hex.EncodeToString(sum[:])
|
||||
dir := path.Join(cacheDir, hash[:2])
|
||||
filename := path.Join(dir, hash)
|
||||
if file, err := os.Open(filename); err == nil {
|
||||
resp := new(Response)
|
||||
err := gob.NewDecoder(file).Decode(resp)
|
||||
file.Close()
|
||||
if resp.StatusCode < 500 {
|
||||
return resp, err
|
||||
}
|
||||
}
|
||||
resp, err := h.Do(request, bodySize)
|
||||
if err != nil || resp.StatusCode >= 500 {
|
||||
return resp, err
|
||||
}
|
||||
if _, err := os.Stat(dir); err != nil {
|
||||
if err := os.MkdirAll(dir, 0750); err != nil {
|
||||
return resp, err
|
||||
}
|
||||
}
|
||||
file, err := os.Create(filename + "~")
|
||||
if err != nil {
|
||||
return resp, err
|
||||
}
|
||||
if err := gob.NewEncoder(file).Encode(resp); err != nil {
|
||||
file.Close()
|
||||
return resp, err
|
||||
}
|
||||
file.Close()
|
||||
return resp, os.Rename(filename+"~", filename)
|
||||
}
|
||||
|
||||
func (h *httpBackend) Do(request *http.Request, bodySize int) (*Response, error) {
|
||||
r := h.GetMatchingRule(request.URL.Host)
|
||||
if r != nil {
|
||||
r.waitChan <- true
|
||||
defer func(r *LimitRule) {
|
||||
randomDelay := time.Duration(0)
|
||||
if r.RandomDelay != 0 {
|
||||
randomDelay = time.Duration(rand.Int63n(int64(r.RandomDelay)))
|
||||
}
|
||||
time.Sleep(r.Delay + randomDelay)
|
||||
<-r.waitChan
|
||||
}(r)
|
||||
}
|
||||
|
||||
res, err := h.Client.Do(request)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
if res.Request != nil {
|
||||
*request = *res.Request
|
||||
}
|
||||
|
||||
var bodyReader io.Reader = res.Body
|
||||
if bodySize > 0 {
|
||||
bodyReader = io.LimitReader(bodyReader, int64(bodySize))
|
||||
}
|
||||
if !res.Uncompressed && res.Header.Get("Content-Encoding") == "gzip" {
|
||||
bodyReader, err = gzip.NewReader(bodyReader)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
body, err := ioutil.ReadAll(bodyReader)
|
||||
defer res.Body.Close()
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &Response{
|
||||
StatusCode: res.StatusCode,
|
||||
Body: body,
|
||||
Headers: &res.Header,
|
||||
}, nil
|
||||
}
|
||||
|
||||
func (h *httpBackend) Limit(rule *LimitRule) error {
|
||||
h.lock.Lock()
|
||||
if h.LimitRules == nil {
|
||||
h.LimitRules = make([]*LimitRule, 0, 8)
|
||||
}
|
||||
h.LimitRules = append(h.LimitRules, rule)
|
||||
h.lock.Unlock()
|
||||
return rule.Init()
|
||||
}
|
||||
|
||||
func (h *httpBackend) Limits(rules []*LimitRule) error {
|
||||
for _, r := range rules {
|
||||
if err := h.Limit(r); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
|
@ -1,180 +0,0 @@
|
|||
// Copyright 2018 Adam Tauber
|
||||
//
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
package colly
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"encoding/json"
|
||||
"io"
|
||||
"io/ioutil"
|
||||
"net/http"
|
||||
"net/url"
|
||||
"strings"
|
||||
"sync/atomic"
|
||||
)
|
||||
|
||||
// Request is the representation of a HTTP request made by a Collector
|
||||
type Request struct {
|
||||
// URL is the parsed URL of the HTTP request
|
||||
URL *url.URL
|
||||
// Headers contains the Request's HTTP headers
|
||||
Headers *http.Header
|
||||
// Ctx is a context between a Request and a Response
|
||||
Ctx *Context
|
||||
// Depth is the number of the parents of the request
|
||||
Depth int
|
||||
// Method is the HTTP method of the request
|
||||
Method string
|
||||
// Body is the request body which is used on POST/PUT requests
|
||||
Body io.Reader
|
||||
// ResponseCharacterencoding is the character encoding of the response body.
|
||||
// Leave it blank to allow automatic character encoding of the response body.
|
||||
// It is empty by default and it can be set in OnRequest callback.
|
||||
ResponseCharacterEncoding string
|
||||
// ID is the Unique identifier of the request
|
||||
ID uint32
|
||||
collector *Collector
|
||||
abort bool
|
||||
baseURL *url.URL
|
||||
// ProxyURL is the proxy address that handles the request
|
||||
ProxyURL string
|
||||
}
|
||||
|
||||
type serializableRequest struct {
|
||||
URL string
|
||||
Method string
|
||||
Body []byte
|
||||
ID uint32
|
||||
Ctx map[string]interface{}
|
||||
Headers http.Header
|
||||
}
|
||||
|
||||
// New creates a new request with the context of the original request
|
||||
func (r *Request) New(method, URL string, body io.Reader) (*Request, error) {
|
||||
u, err := url.Parse(URL)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return &Request{
|
||||
Method: method,
|
||||
URL: u,
|
||||
Body: body,
|
||||
Ctx: r.Ctx,
|
||||
Headers: &http.Header{},
|
||||
ID: atomic.AddUint32(&r.collector.requestCount, 1),
|
||||
collector: r.collector,
|
||||
}, nil
|
||||
}
|
||||
|
||||
// Abort cancels the HTTP request when called in an OnRequest callback
|
||||
func (r *Request) Abort() {
|
||||
r.abort = true
|
||||
}
|
||||
|
||||
// AbsoluteURL returns with the resolved absolute URL of an URL chunk.
|
||||
// AbsoluteURL returns empty string if the URL chunk is a fragment or
|
||||
// could not be parsed
|
||||
func (r *Request) AbsoluteURL(u string) string {
|
||||
if strings.HasPrefix(u, "#") {
|
||||
return ""
|
||||
}
|
||||
var base *url.URL
|
||||
if r.baseURL != nil {
|
||||
base = r.baseURL
|
||||
} else {
|
||||
base = r.URL
|
||||
}
|
||||
absURL, err := base.Parse(u)
|
||||
if err != nil {
|
||||
return ""
|
||||
}
|
||||
absURL.Fragment = ""
|
||||
if absURL.Scheme == "//" {
|
||||
absURL.Scheme = r.URL.Scheme
|
||||
}
|
||||
return absURL.String()
|
||||
}
|
||||
|
||||
// Visit continues Collector's collecting job by creating a
|
||||
// request and preserves the Context of the previous request.
|
||||
// Visit also calls the previously provided callbacks
|
||||
func (r *Request) Visit(URL string) error {
|
||||
return r.collector.scrape(r.AbsoluteURL(URL), "GET", r.Depth+1, nil, r.Ctx, nil, true)
|
||||
}
|
||||
|
||||
// Post continues a collector job by creating a POST request and preserves the Context
|
||||
// of the previous request.
|
||||
// Post also calls the previously provided callbacks
|
||||
func (r *Request) Post(URL string, requestData map[string]string) error {
|
||||
return r.collector.scrape(r.AbsoluteURL(URL), "POST", r.Depth+1, createFormReader(requestData), r.Ctx, nil, true)
|
||||
}
|
||||
|
||||
// PostRaw starts a collector job by creating a POST request with raw binary data.
|
||||
// PostRaw preserves the Context of the previous request
|
||||
// and calls the previously provided callbacks
|
||||
func (r *Request) PostRaw(URL string, requestData []byte) error {
|
||||
return r.collector.scrape(r.AbsoluteURL(URL), "POST", r.Depth+1, bytes.NewReader(requestData), r.Ctx, nil, true)
|
||||
}
|
||||
|
||||
// PostMultipart starts a collector job by creating a Multipart POST request
|
||||
// with raw binary data. PostMultipart also calls the previously provided.
|
||||
// callbacks
|
||||
func (r *Request) PostMultipart(URL string, requestData map[string][]byte) error {
|
||||
boundary := randomBoundary()
|
||||
hdr := http.Header{}
|
||||
hdr.Set("Content-Type", "multipart/form-data; boundary="+boundary)
|
||||
hdr.Set("User-Agent", r.collector.UserAgent)
|
||||
return r.collector.scrape(r.AbsoluteURL(URL), "POST", r.Depth+1, createMultipartReader(boundary, requestData), r.Ctx, hdr, true)
|
||||
}
|
||||
|
||||
// Retry submits HTTP request again with the same parameters
|
||||
func (r *Request) Retry() error {
|
||||
return r.collector.scrape(r.URL.String(), r.Method, r.Depth, r.Body, r.Ctx, *r.Headers, false)
|
||||
}
|
||||
|
||||
// Do submits the request
|
||||
func (r *Request) Do() error {
|
||||
return r.collector.scrape(r.URL.String(), r.Method, r.Depth, r.Body, r.Ctx, *r.Headers, !r.collector.AllowURLRevisit)
|
||||
}
|
||||
|
||||
// Marshal serializes the Request
|
||||
func (r *Request) Marshal() ([]byte, error) {
|
||||
ctx := make(map[string]interface{})
|
||||
if r.Ctx != nil {
|
||||
r.Ctx.ForEach(func(k string, v interface{}) interface{} {
|
||||
ctx[k] = v
|
||||
return nil
|
||||
})
|
||||
}
|
||||
var err error
|
||||
var body []byte
|
||||
if r.Body != nil {
|
||||
body, err = ioutil.ReadAll(r.Body)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
}
|
||||
sr := &serializableRequest{
|
||||
URL: r.URL.String(),
|
||||
Method: r.Method,
|
||||
Body: body,
|
||||
ID: r.ID,
|
||||
Ctx: ctx,
|
||||
}
|
||||
if r.Headers != nil {
|
||||
sr.Headers = *r.Headers
|
||||
}
|
||||
return json.Marshal(sr)
|
||||
}
|
||||
|
|
@ -1,99 +0,0 @@
|
|||
// Copyright 2018 Adam Tauber
|
||||
//
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
package colly
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"io/ioutil"
|
||||
"mime"
|
||||
"net/http"
|
||||
"strings"
|
||||
|
||||
"github.com/saintfish/chardet"
|
||||
"golang.org/x/net/html/charset"
|
||||
)
|
||||
|
||||
// Response is the representation of a HTTP response made by a Collector
|
||||
type Response struct {
|
||||
// StatusCode is the status code of the Response
|
||||
StatusCode int
|
||||
// Body is the content of the Response
|
||||
Body []byte
|
||||
// Ctx is a context between a Request and a Response
|
||||
Ctx *Context
|
||||
// Request is the Request object of the response
|
||||
Request *Request
|
||||
// Headers contains the Response's HTTP headers
|
||||
Headers *http.Header
|
||||
}
|
||||
|
||||
// Save writes response body to disk
|
||||
func (r *Response) Save(fileName string) error {
|
||||
return ioutil.WriteFile(fileName, r.Body, 0644)
|
||||
}
|
||||
|
||||
// FileName returns the sanitized file name parsed from "Content-Disposition"
|
||||
// header or from URL
|
||||
func (r *Response) FileName() string {
|
||||
_, params, err := mime.ParseMediaType(r.Headers.Get("Content-Disposition"))
|
||||
if fName, ok := params["filename"]; ok && err == nil {
|
||||
return SanitizeFileName(fName)
|
||||
}
|
||||
if r.Request.URL.RawQuery != "" {
|
||||
return SanitizeFileName(fmt.Sprintf("%s_%s", r.Request.URL.Path, r.Request.URL.RawQuery))
|
||||
}
|
||||
return SanitizeFileName(strings.TrimPrefix(r.Request.URL.Path, "/"))
|
||||
}
|
||||
|
||||
func (r *Response) fixCharset(detectCharset bool, defaultEncoding string) error {
|
||||
if defaultEncoding != "" {
|
||||
tmpBody, err := encodeBytes(r.Body, "text/plain; charset="+defaultEncoding)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
r.Body = tmpBody
|
||||
return nil
|
||||
}
|
||||
contentType := strings.ToLower(r.Headers.Get("Content-Type"))
|
||||
if !strings.Contains(contentType, "charset") {
|
||||
if !detectCharset {
|
||||
return nil
|
||||
}
|
||||
d := chardet.NewTextDetector()
|
||||
r, err := d.DetectBest(r.Body)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
contentType = "text/plain; charset=" + r.Charset
|
||||
}
|
||||
if strings.Contains(contentType, "utf-8") || strings.Contains(contentType, "utf8") {
|
||||
return nil
|
||||
}
|
||||
tmpBody, err := encodeBytes(r.Body, contentType)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
r.Body = tmpBody
|
||||
return nil
|
||||
}
|
||||
|
||||
func encodeBytes(b []byte, contentType string) ([]byte, error) {
|
||||
r, err := charset.NewReader(bytes.NewReader(b), contentType)
|
||||
if err != nil {
|
||||
return nil, err
|
||||
}
|
||||
return ioutil.ReadAll(r)
|
||||
}
|
||||
|
|
@ -1,128 +0,0 @@
|
|||
// Copyright 2018 Adam Tauber
|
||||
//
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
package storage
|
||||
|
||||
import (
|
||||
"net/http"
|
||||
"net/http/cookiejar"
|
||||
"net/url"
|
||||
"strings"
|
||||
"sync"
|
||||
)
|
||||
|
||||
// Storage is an interface which handles Collector's internal data,
|
||||
// like visited urls and cookies.
|
||||
// The default Storage of the Collector is the InMemoryStorage.
|
||||
// Collector's storage can be changed by calling Collector.SetStorage()
|
||||
// function.
|
||||
type Storage interface {
|
||||
// Init initializes the storage
|
||||
Init() error
|
||||
// Visited receives and stores a request ID that is visited by the Collector
|
||||
Visited(requestID uint64) error
|
||||
// IsVisited returns true if the request was visited before IsVisited
|
||||
// is called
|
||||
IsVisited(requestID uint64) (bool, error)
|
||||
// Cookies retrieves stored cookies for a given host
|
||||
Cookies(u *url.URL) string
|
||||
// SetCookies stores cookies for a given host
|
||||
SetCookies(u *url.URL, cookies string)
|
||||
}
|
||||
|
||||
// InMemoryStorage is the default storage backend of colly.
|
||||
// InMemoryStorage keeps cookies and visited urls in memory
|
||||
// without persisting data on the disk.
|
||||
type InMemoryStorage struct {
|
||||
visitedURLs map[uint64]bool
|
||||
lock *sync.RWMutex
|
||||
jar *cookiejar.Jar
|
||||
}
|
||||
|
||||
// Init initializes InMemoryStorage
|
||||
func (s *InMemoryStorage) Init() error {
|
||||
if s.visitedURLs == nil {
|
||||
s.visitedURLs = make(map[uint64]bool)
|
||||
}
|
||||
if s.lock == nil {
|
||||
s.lock = &sync.RWMutex{}
|
||||
}
|
||||
if s.jar == nil {
|
||||
var err error
|
||||
s.jar, err = cookiejar.New(nil)
|
||||
return err
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
// Visited implements Storage.Visited()
|
||||
func (s *InMemoryStorage) Visited(requestID uint64) error {
|
||||
s.lock.Lock()
|
||||
s.visitedURLs[requestID] = true
|
||||
s.lock.Unlock()
|
||||
return nil
|
||||
}
|
||||
|
||||
// IsVisited implements Storage.IsVisited()
|
||||
func (s *InMemoryStorage) IsVisited(requestID uint64) (bool, error) {
|
||||
s.lock.RLock()
|
||||
visited := s.visitedURLs[requestID]
|
||||
s.lock.RUnlock()
|
||||
return visited, nil
|
||||
}
|
||||
|
||||
// Cookies implements Storage.Cookies()
|
||||
func (s *InMemoryStorage) Cookies(u *url.URL) string {
|
||||
return StringifyCookies(s.jar.Cookies(u))
|
||||
}
|
||||
|
||||
// SetCookies implements Storage.SetCookies()
|
||||
func (s *InMemoryStorage) SetCookies(u *url.URL, cookies string) {
|
||||
s.jar.SetCookies(u, UnstringifyCookies(cookies))
|
||||
}
|
||||
|
||||
// Close implements Storage.Close()
|
||||
func (s *InMemoryStorage) Close() error {
|
||||
return nil
|
||||
}
|
||||
|
||||
// StringifyCookies serializes list of http.Cookies to string
|
||||
func StringifyCookies(cookies []*http.Cookie) string {
|
||||
// Stringify cookies.
|
||||
cs := make([]string, len(cookies))
|
||||
for i, c := range cookies {
|
||||
cs[i] = c.String()
|
||||
}
|
||||
return strings.Join(cs, "\n")
|
||||
}
|
||||
|
||||
// UnstringifyCookies deserializes a cookie string to http.Cookies
|
||||
func UnstringifyCookies(s string) []*http.Cookie {
|
||||
h := http.Header{}
|
||||
for _, c := range strings.Split(s, "\n") {
|
||||
h.Add("Set-Cookie", c)
|
||||
}
|
||||
r := http.Response{Header: h}
|
||||
return r.Cookies()
|
||||
}
|
||||
|
||||
// ContainsCookie checks if a cookie name is represented in cookies
|
||||
func ContainsCookie(cookies []*http.Cookie, name string) bool {
|
||||
for _, c := range cookies {
|
||||
if c.Name == name {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
|
@ -1,171 +0,0 @@
|
|||
// Copyright 2018 Adam Tauber
|
||||
//
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
package colly
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"reflect"
|
||||
"strings"
|
||||
|
||||
"github.com/PuerkitoBio/goquery"
|
||||
)
|
||||
|
||||
// Unmarshal is a shorthand for colly.UnmarshalHTML
|
||||
func (h *HTMLElement) Unmarshal(v interface{}) error {
|
||||
return UnmarshalHTML(v, h.DOM)
|
||||
}
|
||||
|
||||
// UnmarshalHTML declaratively extracts text or attributes to a struct from
|
||||
// HTML response using struct tags composed of css selectors.
|
||||
// Allowed struct tags:
|
||||
// - "selector" (required): CSS (goquery) selector of the desired data
|
||||
// - "attr" (optional): Selects the matching element's attribute's value.
|
||||
// Leave it blank or omit to get the text of the element.
|
||||
//
|
||||
// Example struct declaration:
|
||||
//
|
||||
// type Nested struct {
|
||||
// String string `selector:"div > p"`
|
||||
// Classes []string `selector:"li" attr:"class"`
|
||||
// Struct *Nested `selector:"div > div"`
|
||||
// }
|
||||
//
|
||||
// Supported types: struct, *struct, string, []string
|
||||
func UnmarshalHTML(v interface{}, s *goquery.Selection) error {
|
||||
rv := reflect.ValueOf(v)
|
||||
|
||||
if rv.Kind() != reflect.Ptr || rv.IsNil() {
|
||||
return errors.New("Invalid type or nil-pointer")
|
||||
}
|
||||
|
||||
sv := rv.Elem()
|
||||
st := reflect.TypeOf(v).Elem()
|
||||
|
||||
for i := 0; i < sv.NumField(); i++ {
|
||||
attrV := sv.Field(i)
|
||||
if !attrV.CanAddr() || !attrV.CanSet() {
|
||||
continue
|
||||
}
|
||||
if err := unmarshalAttr(s, attrV, st.Field(i)); err != nil {
|
||||
return err
|
||||
}
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func unmarshalAttr(s *goquery.Selection, attrV reflect.Value, attrT reflect.StructField) error {
|
||||
selector := attrT.Tag.Get("selector")
|
||||
//selector is "-" specify that field should ignore.
|
||||
if selector == "-" {
|
||||
return nil
|
||||
}
|
||||
htmlAttr := attrT.Tag.Get("attr")
|
||||
// TODO support more types
|
||||
switch attrV.Kind() {
|
||||
case reflect.Slice:
|
||||
if err := unmarshalSlice(s, selector, htmlAttr, attrV); err != nil {
|
||||
return err
|
||||
}
|
||||
case reflect.String:
|
||||
val := getDOMValue(s.Find(selector), htmlAttr)
|
||||
attrV.Set(reflect.Indirect(reflect.ValueOf(val)))
|
||||
case reflect.Struct:
|
||||
if err := unmarshalStruct(s, selector, attrV); err != nil {
|
||||
return err
|
||||
}
|
||||
case reflect.Ptr:
|
||||
if err := unmarshalPtr(s, selector, attrV); err != nil {
|
||||
return err
|
||||
}
|
||||
default:
|
||||
return errors.New("Invalid type: " + attrV.String())
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func unmarshalStruct(s *goquery.Selection, selector string, attrV reflect.Value) error {
|
||||
newS := s
|
||||
if selector != "" {
|
||||
newS = newS.Find(selector)
|
||||
}
|
||||
if newS.Nodes == nil {
|
||||
return nil
|
||||
}
|
||||
v := reflect.New(attrV.Type())
|
||||
err := UnmarshalHTML(v.Interface(), newS)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
attrV.Set(reflect.Indirect(v))
|
||||
return nil
|
||||
}
|
||||
|
||||
func unmarshalPtr(s *goquery.Selection, selector string, attrV reflect.Value) error {
|
||||
newS := s
|
||||
if selector != "" {
|
||||
newS = newS.Find(selector)
|
||||
}
|
||||
if newS.Nodes == nil {
|
||||
return nil
|
||||
}
|
||||
e := attrV.Type().Elem()
|
||||
if e.Kind() != reflect.Struct {
|
||||
return errors.New("Invalid slice type")
|
||||
}
|
||||
v := reflect.New(e)
|
||||
err := UnmarshalHTML(v.Interface(), newS)
|
||||
if err != nil {
|
||||
return err
|
||||
}
|
||||
attrV.Set(v)
|
||||
return nil
|
||||
}
|
||||
|
||||
func unmarshalSlice(s *goquery.Selection, selector, htmlAttr string, attrV reflect.Value) error {
|
||||
if attrV.Pointer() == 0 {
|
||||
v := reflect.MakeSlice(attrV.Type(), 0, 0)
|
||||
attrV.Set(v)
|
||||
}
|
||||
switch attrV.Type().Elem().Kind() {
|
||||
case reflect.String:
|
||||
s.Find(selector).Each(func(_ int, s *goquery.Selection) {
|
||||
val := getDOMValue(s, htmlAttr)
|
||||
attrV.Set(reflect.Append(attrV, reflect.Indirect(reflect.ValueOf(val))))
|
||||
})
|
||||
case reflect.Ptr:
|
||||
s.Find(selector).Each(func(_ int, innerSel *goquery.Selection) {
|
||||
someVal := reflect.New(attrV.Type().Elem().Elem())
|
||||
UnmarshalHTML(someVal.Interface(), innerSel)
|
||||
attrV.Set(reflect.Append(attrV, someVal))
|
||||
})
|
||||
case reflect.Struct:
|
||||
s.Find(selector).Each(func(_ int, innerSel *goquery.Selection) {
|
||||
someVal := reflect.New(attrV.Type().Elem())
|
||||
UnmarshalHTML(someVal.Interface(), innerSel)
|
||||
attrV.Set(reflect.Append(attrV, reflect.Indirect(someVal)))
|
||||
})
|
||||
default:
|
||||
return errors.New("Invalid slice type")
|
||||
}
|
||||
return nil
|
||||
}
|
||||
|
||||
func getDOMValue(s *goquery.Selection, attr string) string {
|
||||
if attr == "" {
|
||||
return strings.TrimSpace(s.First().Text())
|
||||
}
|
||||
attrV, _ := s.Attr(attr)
|
||||
return attrV
|
||||
}
|
||||
|
|
@ -1,170 +0,0 @@
|
|||
// Copyright 2018 Adam Tauber
|
||||
//
|
||||
// Licensed under the Apache License, Version 2.0 (the "License");
|
||||
// you may not use this file except in compliance with the License.
|
||||
// You may obtain a copy of the License at
|
||||
//
|
||||
// http://www.apache.org/licenses/LICENSE-2.0
|
||||
//
|
||||
// Unless required by applicable law or agreed to in writing, software
|
||||
// distributed under the License is distributed on an "AS IS" BASIS,
|
||||
// WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
|
||||
// See the License for the specific language governing permissions and
|
||||
// limitations under the License.
|
||||
|
||||
package colly
|
||||
|
||||
import (
|
||||
"encoding/xml"
|
||||
"strings"
|
||||
|
||||
"github.com/antchfx/htmlquery"
|
||||
"github.com/antchfx/xmlquery"
|
||||
"golang.org/x/net/html"
|
||||
)
|
||||
|
||||
// XMLElement is the representation of a XML tag.
|
||||
type XMLElement struct {
|
||||
// Name is the name of the tag
|
||||
Name string
|
||||
Text string
|
||||
attributes interface{}
|
||||
// Request is the request object of the element's HTML document
|
||||
Request *Request
|
||||
// Response is the Response object of the element's HTML document
|
||||
Response *Response
|
||||
// DOM is the DOM object of the page. DOM is relative
|
||||
// to the current XMLElement and is either a html.Node or xmlquery.Node
|
||||
// based on how the XMLElement was created.
|
||||
DOM interface{}
|
||||
isHTML bool
|
||||
}
|
||||
|
||||
// NewXMLElementFromHTMLNode creates a XMLElement from a html.Node.
|
||||
func NewXMLElementFromHTMLNode(resp *Response, s *html.Node) *XMLElement {
|
||||
return &XMLElement{
|
||||
Name: s.Data,
|
||||
Request: resp.Request,
|
||||
Response: resp,
|
||||
Text: htmlquery.InnerText(s),
|
||||
DOM: s,
|
||||
attributes: s.Attr,
|
||||
isHTML: true,
|
||||
}
|
||||
}
|
||||
|
||||
// NewXMLElementFromXMLNode creates a XMLElement from a xmlquery.Node.
|
||||
func NewXMLElementFromXMLNode(resp *Response, s *xmlquery.Node) *XMLElement {
|
||||
return &XMLElement{
|
||||
Name: s.Data,
|
||||
Request: resp.Request,
|
||||
Response: resp,
|
||||
Text: s.InnerText(),
|
||||
DOM: s,
|
||||
attributes: s.Attr,
|
||||
isHTML: false,
|
||||
}
|
||||
}
|
||||
|
||||
// Attr returns the selected attribute of a HTMLElement or empty string
|
||||
// if no attribute found
|
||||
func (h *XMLElement) Attr(k string) string {
|
||||
if h.isHTML {
|
||||
for _, a := range h.attributes.([]html.Attribute) {
|
||||
if a.Key == k {
|
||||
return a.Val
|
||||
}
|
||||
}
|
||||
} else {
|
||||
for _, a := range h.attributes.([]xml.Attr) {
|
||||
if a.Name.Local == k {
|
||||
return a.Value
|
||||
}
|
||||
}
|
||||
}
|
||||
return ""
|
||||
}
|
||||
|
||||
// ChildText returns the concatenated and stripped text content of the matching
|
||||
// elements.
|
||||
func (h *XMLElement) ChildText(xpathQuery string) string {
|
||||
if h.isHTML {
|
||||
child := htmlquery.FindOne(h.DOM.(*html.Node), xpathQuery)
|
||||
if child == nil {
|
||||
return ""
|
||||
}
|
||||
return strings.TrimSpace(htmlquery.InnerText(child))
|
||||
}
|
||||
child := xmlquery.FindOne(h.DOM.(*xmlquery.Node), xpathQuery)
|
||||
if child == nil {
|
||||
return ""
|
||||
}
|
||||
return strings.TrimSpace(child.InnerText())
|
||||
|
||||
}
|
||||
|
||||
// ChildAttr returns the stripped text content of the first matching
|
||||
// element's attribute.
|
||||
func (h *XMLElement) ChildAttr(xpathQuery, attrName string) string {
|
||||
if h.isHTML {
|
||||
child := htmlquery.FindOne(h.DOM.(*html.Node), xpathQuery)
|
||||
if child != nil {
|
||||
for _, attr := range child.Attr {
|
||||
if attr.Key == attrName {
|
||||
return strings.TrimSpace(attr.Val)
|
||||
}
|
||||
}
|
||||
}
|
||||
} else {
|
||||
child := xmlquery.FindOne(h.DOM.(*xmlquery.Node), xpathQuery)
|
||||
if child != nil {
|
||||
for _, attr := range child.Attr {
|
||||
if attr.Name.Local == attrName {
|
||||
return strings.TrimSpace(attr.Value)
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
return ""
|
||||
}
|
||||
|
||||
// ChildAttrs returns the stripped text content of all the matching
|
||||
// element's attributes.
|
||||
func (h *XMLElement) ChildAttrs(xpathQuery, attrName string) []string {
|
||||
var res []string
|
||||
if h.isHTML {
|
||||
for _, child := range htmlquery.Find(h.DOM.(*html.Node), xpathQuery) {
|
||||
for _, attr := range child.Attr {
|
||||
if attr.Key == attrName {
|
||||
res = append(res, strings.TrimSpace(attr.Val))
|
||||
}
|
||||
}
|
||||
}
|
||||
} else {
|
||||
xmlquery.FindEach(h.DOM.(*xmlquery.Node), xpathQuery, func(i int, child *xmlquery.Node) {
|
||||
for _, attr := range child.Attr {
|
||||
if attr.Name.Local == attrName {
|
||||
res = append(res, strings.TrimSpace(attr.Value))
|
||||
}
|
||||
}
|
||||
})
|
||||
}
|
||||
return res
|
||||
}
|
||||
|
||||
// ChildTexts returns an array of strings corresponding to child elements that match the xpath query.
|
||||
// Each item in the array is the stripped text content of the corresponding matching child element.
|
||||
func (h *XMLElement) ChildTexts(xpathQuery string) []string {
|
||||
texts := make([]string, 0)
|
||||
if h.isHTML {
|
||||
for _, child := range htmlquery.Find(h.DOM.(*html.Node), xpathQuery) {
|
||||
texts = append(texts, strings.TrimSpace(htmlquery.InnerText(child)))
|
||||
}
|
||||
} else {
|
||||
xmlquery.FindEach(h.DOM.(*xmlquery.Node), xpathQuery, func(i int, child *xmlquery.Node) {
|
||||
texts = append(texts, strings.TrimSpace(child.InnerText()))
|
||||
})
|
||||
}
|
||||
return texts
|
||||
}
|
||||
|
|
@ -1,22 +0,0 @@
|
|||
# Compiled Object files, Static and Dynamic libs (Shared Objects)
|
||||
*.o
|
||||
*.a
|
||||
*.so
|
||||
|
||||
# Folders
|
||||
_obj
|
||||
_test
|
||||
|
||||
# Architecture specific extensions/prefixes
|
||||
*.[568vq]
|
||||
[568vq].out
|
||||
|
||||
*.cgo1.go
|
||||
*.cgo2.c
|
||||
_cgo_defun.c
|
||||
_cgo_gotypes.go
|
||||
_cgo_export.*
|
||||
|
||||
_testmain.go
|
||||
|
||||
*.exe
|
||||
|
|
@ -1 +0,0 @@
|
|||
language: go
|
||||
|
|
@ -1,27 +0,0 @@
|
|||
Copyright (c) 2017 Mechanism Design. All rights reserved.
|
||||
|
||||
Redistribution and use in source and binary forms, with or without
|
||||
modification, are permitted provided that the following conditions are
|
||||
met:
|
||||
|
||||
* Redistributions of source code must retain the above copyright
|
||||
notice, this list of conditions and the following disclaimer.
|
||||
* Redistributions in binary form must reproduce the above
|
||||
copyright notice, this list of conditions and the following disclaimer
|
||||
in the documentation and/or other materials provided with the
|
||||
distribution.
|
||||
* Neither the name of Google Inc. nor the names of its
|
||||
contributors may be used to endorse or promote products derived from
|
||||
this software without specific prior written permission.
|
||||
|
||||
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS
|
||||
"AS IS" AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT
|
||||
LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR
|
||||
A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT
|
||||
OWNER OR CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL,
|
||||
SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT
|
||||
LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF USE,
|
||||
DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND ON ANY
|
||||
THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
|
||||
(INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
|
||||
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
|
||||
|
|
@ -1,62 +0,0 @@
|
|||
sanitize [](https://godoc.org/github.com/kennygrant/sanitize) [](https://goreportcard.com/report/github.com/kennygrant/sanitize) [](https://circleci.com/gh/kennygrant/sanitize)
|
||||
========
|
||||
|
||||
Package sanitize provides functions to sanitize html and paths with go (golang).
|
||||
|
||||
FUNCTIONS
|
||||
|
||||
|
||||
```go
|
||||
sanitize.Accents(s string) string
|
||||
```
|
||||
|
||||
Accents replaces a set of accented characters with ascii equivalents.
|
||||
|
||||
```go
|
||||
sanitize.BaseName(s string) string
|
||||
```
|
||||
|
||||
BaseName makes a string safe to use in a file name, producing a sanitized basename replacing . or / with -. Unlike Name no attempt is made to normalise text as a path.
|
||||
|
||||
```go
|
||||
sanitize.HTML(s string) string
|
||||
```
|
||||
|
||||
HTML strips html tags with a very simple parser, replace common entities, and escape < and > in the result. The result is intended to be used as plain text.
|
||||
|
||||
```go
|
||||
sanitize.HTMLAllowing(s string, args...[]string) (string, error)
|
||||
```
|
||||
|
||||
HTMLAllowing parses html and allow certain tags and attributes from the lists optionally specified by args - args[0] is a list of allowed tags, args[1] is a list of allowed attributes. If either is missing default sets are used.
|
||||
|
||||
```go
|
||||
sanitize.Name(s string) string
|
||||
```
|
||||
|
||||
Name makes a string safe to use in a file name by first finding the path basename, then replacing non-ascii characters.
|
||||
|
||||
```go
|
||||
sanitize.Path(s string) string
|
||||
```
|
||||
|
||||
Path makes a string safe to use as an url path.
|
||||
|
||||
|
||||
Changes
|
||||
-------
|
||||
|
||||
Version 1.2
|
||||
|
||||
Adjusted HTML function to avoid linter warning
|
||||
Added more tests from https://githubengineering.com/githubs-post-csp-journey/
|
||||
Chnaged name of license file
|
||||
Added badges and change log to readme
|
||||
|
||||
Version 1.1
|
||||
Fixed type in comments.
|
||||
Merge pull request from Povilas Balzaravicius Pawka
|
||||
- replace br tags with newline even when they contain a space
|
||||
|
||||
Version 1.0
|
||||
First release
|
||||
|
|
@ -1,388 +0,0 @@
|
|||
// Package sanitize provides functions for sanitizing text.
|
||||
package sanitize
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"html"
|
||||
"html/template"
|
||||
"io"
|
||||
"path"
|
||||
"regexp"
|
||||
"strings"
|
||||
|
||||
parser "golang.org/x/net/html"
|
||||
)
|
||||
|
||||
var (
|
||||
ignoreTags = []string{"title", "script", "style", "iframe", "frame", "frameset", "noframes", "noembed", "embed", "applet", "object", "base"}
|
||||
|
||||
defaultTags = []string{"h1", "h2", "h3", "h4", "h5", "h6", "div", "span", "hr", "p", "br", "b", "i", "strong", "em", "ol", "ul", "li", "a", "img", "pre", "code", "blockquote", "article", "section"}
|
||||
|
||||
defaultAttributes = []string{"id", "class", "src", "href", "title", "alt", "name", "rel"}
|
||||
)
|
||||
|
||||
// HTMLAllowing sanitizes html, allowing some tags.
|
||||
// Arrays of allowed tags and allowed attributes may optionally be passed as the second and third arguments.
|
||||
func HTMLAllowing(s string, args ...[]string) (string, error) {
|
||||
|
||||
allowedTags := defaultTags
|
||||
if len(args) > 0 {
|
||||
allowedTags = args[0]
|
||||
}
|
||||
allowedAttributes := defaultAttributes
|
||||
if len(args) > 1 {
|
||||
allowedAttributes = args[1]
|
||||
}
|
||||
|
||||
// Parse the html
|
||||
tokenizer := parser.NewTokenizer(strings.NewReader(s))
|
||||
|
||||
buffer := bytes.NewBufferString("")
|
||||
ignore := ""
|
||||
|
||||
for {
|
||||
tokenType := tokenizer.Next()
|
||||
token := tokenizer.Token()
|
||||
|
||||
switch tokenType {
|
||||
|
||||
case parser.ErrorToken:
|
||||
err := tokenizer.Err()
|
||||
if err == io.EOF {
|
||||
return buffer.String(), nil
|
||||
}
|
||||
return "", err
|
||||
|
||||
case parser.StartTagToken:
|
||||
|
||||
if len(ignore) == 0 && includes(allowedTags, token.Data) {
|
||||
token.Attr = cleanAttributes(token.Attr, allowedAttributes)
|
||||
buffer.WriteString(token.String())
|
||||
} else if includes(ignoreTags, token.Data) {
|
||||
ignore = token.Data
|
||||
}
|
||||
|
||||
case parser.SelfClosingTagToken:
|
||||
|
||||
if len(ignore) == 0 && includes(allowedTags, token.Data) {
|
||||
token.Attr = cleanAttributes(token.Attr, allowedAttributes)
|
||||
buffer.WriteString(token.String())
|
||||
} else if token.Data == ignore {
|
||||
ignore = ""
|
||||
}
|
||||
|
||||
case parser.EndTagToken:
|
||||
if len(ignore) == 0 && includes(allowedTags, token.Data) {
|
||||
token.Attr = []parser.Attribute{}
|
||||
buffer.WriteString(token.String())
|
||||
} else if token.Data == ignore {
|
||||
ignore = ""
|
||||
}
|
||||
|
||||
case parser.TextToken:
|
||||
// We allow text content through, unless ignoring this entire tag and its contents (including other tags)
|
||||
if ignore == "" {
|
||||
buffer.WriteString(token.String())
|
||||
}
|
||||
case parser.CommentToken:
|
||||
// We ignore comments by default
|
||||
case parser.DoctypeToken:
|
||||
// We ignore doctypes by default - html5 does not require them and this is intended for sanitizing snippets of text
|
||||
default:
|
||||
// We ignore unknown token types by default
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
}
|
||||
|
||||
// HTML strips html tags, replace common entities, and escapes <>&;'" in the result.
|
||||
// Note the returned text may contain entities as it is escaped by HTMLEscapeString, and most entities are not translated.
|
||||
func HTML(s string) (output string) {
|
||||
|
||||
// Shortcut strings with no tags in them
|
||||
if !strings.ContainsAny(s, "<>") {
|
||||
output = s
|
||||
} else {
|
||||
|
||||
// First remove line breaks etc as these have no meaning outside html tags (except pre)
|
||||
// this means pre sections will lose formatting... but will result in less unintentional paras.
|
||||
s = strings.Replace(s, "\n", "", -1)
|
||||
|
||||
// Then replace line breaks with newlines, to preserve that formatting
|
||||
s = strings.Replace(s, "</p>", "\n", -1)
|
||||
s = strings.Replace(s, "<br>", "\n", -1)
|
||||
s = strings.Replace(s, "</br>", "\n", -1)
|
||||
s = strings.Replace(s, "<br/>", "\n", -1)
|
||||
s = strings.Replace(s, "<br />", "\n", -1)
|
||||
|
||||
// Walk through the string removing all tags
|
||||
b := bytes.NewBufferString("")
|
||||
inTag := false
|
||||
for _, r := range s {
|
||||
switch r {
|
||||
case '<':
|
||||
inTag = true
|
||||
case '>':
|
||||
inTag = false
|
||||
default:
|
||||
if !inTag {
|
||||
b.WriteRune(r)
|
||||
}
|
||||
}
|
||||
}
|
||||
output = b.String()
|
||||
}
|
||||
|
||||
// Remove a few common harmless entities, to arrive at something more like plain text
|
||||
output = strings.Replace(output, "‘", "'", -1)
|
||||
output = strings.Replace(output, "’", "'", -1)
|
||||
output = strings.Replace(output, "“", "\"", -1)
|
||||
output = strings.Replace(output, "”", "\"", -1)
|
||||
output = strings.Replace(output, " ", " ", -1)
|
||||
output = strings.Replace(output, """, "\"", -1)
|
||||
output = strings.Replace(output, "'", "'", -1)
|
||||
|
||||
// Translate some entities into their plain text equivalent (for example accents, if encoded as entities)
|
||||
output = html.UnescapeString(output)
|
||||
|
||||
// In case we have missed any tags above, escape the text - removes <, >, &, ' and ".
|
||||
output = template.HTMLEscapeString(output)
|
||||
|
||||
// After processing, remove some harmless entities &, ' and " which are encoded by HTMLEscapeString
|
||||
output = strings.Replace(output, """, "\"", -1)
|
||||
output = strings.Replace(output, "'", "'", -1)
|
||||
output = strings.Replace(output, "& ", "& ", -1) // NB space after
|
||||
output = strings.Replace(output, "&amp; ", "& ", -1) // NB space after
|
||||
|
||||
return output
|
||||
}
|
||||
|
||||
// We are very restrictive as this is intended for ascii url slugs
|
||||
var illegalPath = regexp.MustCompile(`[^[:alnum:]\~\-\./]`)
|
||||
|
||||
// Path makes a string safe to use as a URL path,
|
||||
// removing accents and replacing separators with -.
|
||||
// The path may still start at / and is not intended
|
||||
// for use as a file system path without prefix.
|
||||
func Path(s string) string {
|
||||
// Start with lowercase string
|
||||
filePath := strings.ToLower(s)
|
||||
filePath = strings.Replace(filePath, "..", "", -1)
|
||||
filePath = path.Clean(filePath)
|
||||
|
||||
// Remove illegal characters for paths, flattening accents
|
||||
// and replacing some common separators with -
|
||||
filePath = cleanString(filePath, illegalPath)
|
||||
|
||||
// NB this may be of length 0, caller must check
|
||||
return filePath
|
||||
}
|
||||
|
||||
// Remove all other unrecognised characters apart from
|
||||
var illegalName = regexp.MustCompile(`[^[:alnum:]-.]`)
|
||||
|
||||
// Name makes a string safe to use in a file name by first finding the path basename, then replacing non-ascii characters.
|
||||
func Name(s string) string {
|
||||
// Start with lowercase string
|
||||
fileName := strings.ToLower(s)
|
||||
fileName = path.Clean(path.Base(fileName))
|
||||
|
||||
// Remove illegal characters for names, replacing some common separators with -
|
||||
fileName = cleanString(fileName, illegalName)
|
||||
|
||||
// NB this may be of length 0, caller must check
|
||||
return fileName
|
||||
}
|
||||
|
||||
// Replace these separators with -
|
||||
var baseNameSeparators = regexp.MustCompile(`[./]`)
|
||||
|
||||
// BaseName makes a string safe to use in a file name, producing a sanitized basename replacing . or / with -.
|
||||
// No attempt is made to normalise a path or normalise case.
|
||||
func BaseName(s string) string {
|
||||
|
||||
// Replace certain joining characters with a dash
|
||||
baseName := baseNameSeparators.ReplaceAllString(s, "-")
|
||||
|
||||
// Remove illegal characters for names, replacing some common separators with -
|
||||
baseName = cleanString(baseName, illegalName)
|
||||
|
||||
// NB this may be of length 0, caller must check
|
||||
return baseName
|
||||
}
|
||||
|
||||
// A very limited list of transliterations to catch common european names translated to urls.
|
||||
// This set could be expanded with at least caps and many more characters.
|
||||
var transliterations = map[rune]string{
|
||||
'À': "A",
|
||||
'Á': "A",
|
||||
'Â': "A",
|
||||
'Ã': "A",
|
||||
'Ä': "A",
|
||||
'Å': "AA",
|
||||
'Æ': "AE",
|
||||
'Ç': "C",
|
||||
'È': "E",
|
||||
'É': "E",
|
||||
'Ê': "E",
|
||||
'Ë': "E",
|
||||
'Ì': "I",
|
||||
'Í': "I",
|
||||
'Î': "I",
|
||||
'Ï': "I",
|
||||
'Ð': "D",
|
||||
'Ł': "L",
|
||||
'Ñ': "N",
|
||||
'Ò': "O",
|
||||
'Ó': "O",
|
||||
'Ô': "O",
|
||||
'Õ': "O",
|
||||
'Ö': "OE",
|
||||
'Ø': "OE",
|
||||
'Œ': "OE",
|
||||
'Ù': "U",
|
||||
'Ú': "U",
|
||||
'Ü': "UE",
|
||||
'Û': "U",
|
||||
'Ý': "Y",
|
||||
'Þ': "TH",
|
||||
'ẞ': "SS",
|
||||
'à': "a",
|
||||
'á': "a",
|
||||
'â': "a",
|
||||
'ã': "a",
|
||||
'ä': "ae",
|
||||
'å': "aa",
|
||||
'æ': "ae",
|
||||
'ç': "c",
|
||||
'è': "e",
|
||||
'é': "e",
|
||||
'ê': "e",
|
||||
'ë': "e",
|
||||
'ì': "i",
|
||||
'í': "i",
|
||||
'î': "i",
|
||||
'ï': "i",
|
||||
'ð': "d",
|
||||
'ł': "l",
|
||||
'ñ': "n",
|
||||
'ń': "n",
|
||||
'ò': "o",
|
||||
'ó': "o",
|
||||
'ô': "o",
|
||||
'õ': "o",
|
||||
'ō': "o",
|
||||
'ö': "oe",
|
||||
'ø': "oe",
|
||||
'œ': "oe",
|
||||
'ś': "s",
|
||||
'ù': "u",
|
||||
'ú': "u",
|
||||
'û': "u",
|
||||
'ū': "u",
|
||||
'ü': "ue",
|
||||
'ý': "y",
|
||||
'ÿ': "y",
|
||||
'ż': "z",
|
||||
'þ': "th",
|
||||
'ß': "ss",
|
||||
}
|
||||
|
||||
// Accents replaces a set of accented characters with ascii equivalents.
|
||||
func Accents(s string) string {
|
||||
// Replace some common accent characters
|
||||
b := bytes.NewBufferString("")
|
||||
for _, c := range s {
|
||||
// Check transliterations first
|
||||
if val, ok := transliterations[c]; ok {
|
||||
b.WriteString(val)
|
||||
} else {
|
||||
b.WriteRune(c)
|
||||
}
|
||||
}
|
||||
return b.String()
|
||||
}
|
||||
|
||||
var (
|
||||
// If the attribute contains data: or javascript: anywhere, ignore it
|
||||
// we don't allow this in attributes as it is so frequently used for xss
|
||||
// NB we allow spaces in the value, and lowercase.
|
||||
illegalAttr = regexp.MustCompile(`(d\s*a\s*t\s*a|j\s*a\s*v\s*a\s*s\s*c\s*r\s*i\s*p\s*t\s*)\s*:`)
|
||||
|
||||
// We are far more restrictive with href attributes.
|
||||
legalHrefAttr = regexp.MustCompile(`\A[/#][^/\\]?|mailto:|http://|https://`)
|
||||
)
|
||||
|
||||
// cleanAttributes returns an array of attributes after removing malicious ones.
|
||||
func cleanAttributes(a []parser.Attribute, allowed []string) []parser.Attribute {
|
||||
if len(a) == 0 {
|
||||
return a
|
||||
}
|
||||
|
||||
var cleaned []parser.Attribute
|
||||
for _, attr := range a {
|
||||
if includes(allowed, attr.Key) {
|
||||
|
||||
val := strings.ToLower(attr.Val)
|
||||
|
||||
// Check for illegal attribute values
|
||||
if illegalAttr.FindString(val) != "" {
|
||||
attr.Val = ""
|
||||
}
|
||||
|
||||
// Check for legal href values - / mailto:// http:// or https://
|
||||
if attr.Key == "href" {
|
||||
if legalHrefAttr.FindString(val) == "" {
|
||||
attr.Val = ""
|
||||
}
|
||||
}
|
||||
|
||||
// If we still have an attribute, append it to the array
|
||||
if attr.Val != "" {
|
||||
cleaned = append(cleaned, attr)
|
||||
}
|
||||
}
|
||||
}
|
||||
return cleaned
|
||||
}
|
||||
|
||||
// A list of characters we consider separators in normal strings and replace with our canonical separator - rather than removing.
|
||||
var (
|
||||
separators = regexp.MustCompile(`[ &_=+:]`)
|
||||
|
||||
dashes = regexp.MustCompile(`[\-]+`)
|
||||
)
|
||||
|
||||
// cleanString replaces separators with - and removes characters listed in the regexp provided from string.
|
||||
// Accents, spaces, and all characters not in A-Za-z0-9 are replaced.
|
||||
func cleanString(s string, r *regexp.Regexp) string {
|
||||
|
||||
// Remove any trailing space to avoid ending on -
|
||||
s = strings.Trim(s, " ")
|
||||
|
||||
// Flatten accents first so that if we remove non-ascii we still get a legible name
|
||||
s = Accents(s)
|
||||
|
||||
// Replace certain joining characters with a dash
|
||||
s = separators.ReplaceAllString(s, "-")
|
||||
|
||||
// Remove all other unrecognised characters - NB we do allow any printable characters
|
||||
s = r.ReplaceAllString(s, "")
|
||||
|
||||
// Remove any multiple dashes caused by replacements above
|
||||
s = dashes.ReplaceAllString(s, "-")
|
||||
|
||||
return s
|
||||
}
|
||||
|
||||
// includes checks for inclusion of a string in a []string.
|
||||
func includes(a []string, s string) bool {
|
||||
for _, as := range a {
|
||||
if as == s {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
|
@ -1,102 +0,0 @@
|
|||
package chardet
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
)
|
||||
|
||||
type recognizer2022 struct {
|
||||
charset string
|
||||
escapes [][]byte
|
||||
}
|
||||
|
||||
func (r *recognizer2022) Match(input *recognizerInput) (output recognizerOutput) {
|
||||
return recognizerOutput{
|
||||
Charset: r.charset,
|
||||
Confidence: r.matchConfidence(input.input),
|
||||
}
|
||||
}
|
||||
|
||||
func (r *recognizer2022) matchConfidence(input []byte) int {
|
||||
var hits, misses, shifts int
|
||||
input:
|
||||
for i := 0; i < len(input); i++ {
|
||||
c := input[i]
|
||||
if c == 0x1B {
|
||||
for _, esc := range r.escapes {
|
||||
if bytes.HasPrefix(input[i+1:], esc) {
|
||||
hits++
|
||||
i += len(esc)
|
||||
continue input
|
||||
}
|
||||
}
|
||||
misses++
|
||||
} else if c == 0x0E || c == 0x0F {
|
||||
shifts++
|
||||
}
|
||||
}
|
||||
if hits == 0 {
|
||||
return 0
|
||||
}
|
||||
quality := (100*hits - 100*misses) / (hits + misses)
|
||||
if hits+shifts < 5 {
|
||||
quality -= (5 - (hits + shifts)) * 10
|
||||
}
|
||||
if quality < 0 {
|
||||
quality = 0
|
||||
}
|
||||
return quality
|
||||
}
|
||||
|
||||
var escapeSequences_2022JP = [][]byte{
|
||||
{0x24, 0x28, 0x43}, // KS X 1001:1992
|
||||
{0x24, 0x28, 0x44}, // JIS X 212-1990
|
||||
{0x24, 0x40}, // JIS C 6226-1978
|
||||
{0x24, 0x41}, // GB 2312-80
|
||||
{0x24, 0x42}, // JIS X 208-1983
|
||||
{0x26, 0x40}, // JIS X 208 1990, 1997
|
||||
{0x28, 0x42}, // ASCII
|
||||
{0x28, 0x48}, // JIS-Roman
|
||||
{0x28, 0x49}, // Half-width katakana
|
||||
{0x28, 0x4a}, // JIS-Roman
|
||||
{0x2e, 0x41}, // ISO 8859-1
|
||||
{0x2e, 0x46}, // ISO 8859-7
|
||||
}
|
||||
|
||||
var escapeSequences_2022KR = [][]byte{
|
||||
{0x24, 0x29, 0x43},
|
||||
}
|
||||
|
||||
var escapeSequences_2022CN = [][]byte{
|
||||
{0x24, 0x29, 0x41}, // GB 2312-80
|
||||
{0x24, 0x29, 0x47}, // CNS 11643-1992 Plane 1
|
||||
{0x24, 0x2A, 0x48}, // CNS 11643-1992 Plane 2
|
||||
{0x24, 0x29, 0x45}, // ISO-IR-165
|
||||
{0x24, 0x2B, 0x49}, // CNS 11643-1992 Plane 3
|
||||
{0x24, 0x2B, 0x4A}, // CNS 11643-1992 Plane 4
|
||||
{0x24, 0x2B, 0x4B}, // CNS 11643-1992 Plane 5
|
||||
{0x24, 0x2B, 0x4C}, // CNS 11643-1992 Plane 6
|
||||
{0x24, 0x2B, 0x4D}, // CNS 11643-1992 Plane 7
|
||||
{0x4e}, // SS2
|
||||
{0x4f}, // SS3
|
||||
}
|
||||
|
||||
func newRecognizer_2022JP() *recognizer2022 {
|
||||
return &recognizer2022{
|
||||
"ISO-2022-JP",
|
||||
escapeSequences_2022JP,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_2022KR() *recognizer2022 {
|
||||
return &recognizer2022{
|
||||
"ISO-2022-KR",
|
||||
escapeSequences_2022KR,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_2022CN() *recognizer2022 {
|
||||
return &recognizer2022{
|
||||
"ISO-2022-CN",
|
||||
escapeSequences_2022CN,
|
||||
}
|
||||
}
|
||||
|
|
@ -1 +0,0 @@
|
|||
Sheng Yu (yusheng dot sjtu at gmail dot com)
|
||||
|
|
@ -1,22 +0,0 @@
|
|||
Copyright (c) 2012 chardet Authors
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy of
|
||||
this software and associated documentation files (the "Software"), to deal in
|
||||
the Software without restriction, including without limitation the rights to
|
||||
use, copy, modify, merge, publish, distribute, sublicense, and/or sell copies
|
||||
of the Software, and to permit persons to whom the Software is furnished to do
|
||||
so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in all
|
||||
copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
|
||||
SOFTWARE.
|
||||
|
||||
Partial of the Software is derived from ICU project. See icu-license.html for
|
||||
license of the derivative portions.
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
# chardet
|
||||
|
||||
chardet is library to automatically detect
|
||||
[charset](http://en.wikipedia.org/wiki/Character_encoding) of texts for [Go
|
||||
programming language](http://golang.org/). It's based on the algorithm and data
|
||||
in [ICU](http://icu-project.org/)'s implementation.
|
||||
|
||||
## Documentation and Usage
|
||||
|
||||
See [pkgdoc](http://go.pkgdoc.org/github.com/saintfish/chardet)
|
||||
|
|
@ -1,136 +0,0 @@
|
|||
// Package chardet ports character set detection from ICU.
|
||||
package chardet
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"sort"
|
||||
)
|
||||
|
||||
// Result contains all the information that charset detector gives.
|
||||
type Result struct {
|
||||
// IANA name of the detected charset.
|
||||
Charset string
|
||||
// IANA name of the detected language. It may be empty for some charsets.
|
||||
Language string
|
||||
// Confidence of the Result. Scale from 1 to 100. The bigger, the more confident.
|
||||
Confidence int
|
||||
}
|
||||
|
||||
// Detector implements charset detection.
|
||||
type Detector struct {
|
||||
recognizers []recognizer
|
||||
stripTag bool
|
||||
}
|
||||
|
||||
// List of charset recognizers
|
||||
var recognizers = []recognizer{
|
||||
newRecognizer_utf8(),
|
||||
newRecognizer_utf16be(),
|
||||
newRecognizer_utf16le(),
|
||||
newRecognizer_utf32be(),
|
||||
newRecognizer_utf32le(),
|
||||
newRecognizer_8859_1_en(),
|
||||
newRecognizer_8859_1_da(),
|
||||
newRecognizer_8859_1_de(),
|
||||
newRecognizer_8859_1_es(),
|
||||
newRecognizer_8859_1_fr(),
|
||||
newRecognizer_8859_1_it(),
|
||||
newRecognizer_8859_1_nl(),
|
||||
newRecognizer_8859_1_no(),
|
||||
newRecognizer_8859_1_pt(),
|
||||
newRecognizer_8859_1_sv(),
|
||||
newRecognizer_8859_2_cs(),
|
||||
newRecognizer_8859_2_hu(),
|
||||
newRecognizer_8859_2_pl(),
|
||||
newRecognizer_8859_2_ro(),
|
||||
newRecognizer_8859_5_ru(),
|
||||
newRecognizer_8859_6_ar(),
|
||||
newRecognizer_8859_7_el(),
|
||||
newRecognizer_8859_8_I_he(),
|
||||
newRecognizer_8859_8_he(),
|
||||
newRecognizer_windows_1251(),
|
||||
newRecognizer_windows_1256(),
|
||||
newRecognizer_KOI8_R(),
|
||||
newRecognizer_8859_9_tr(),
|
||||
|
||||
newRecognizer_sjis(),
|
||||
newRecognizer_gb_18030(),
|
||||
newRecognizer_euc_jp(),
|
||||
newRecognizer_euc_kr(),
|
||||
newRecognizer_big5(),
|
||||
|
||||
newRecognizer_2022JP(),
|
||||
newRecognizer_2022KR(),
|
||||
newRecognizer_2022CN(),
|
||||
|
||||
newRecognizer_IBM424_he_rtl(),
|
||||
newRecognizer_IBM424_he_ltr(),
|
||||
newRecognizer_IBM420_ar_rtl(),
|
||||
newRecognizer_IBM420_ar_ltr(),
|
||||
}
|
||||
|
||||
// NewTextDetector creates a Detector for plain text.
|
||||
func NewTextDetector() *Detector {
|
||||
return &Detector{recognizers, false}
|
||||
}
|
||||
|
||||
// NewHtmlDetector creates a Detector for Html.
|
||||
func NewHtmlDetector() *Detector {
|
||||
return &Detector{recognizers, true}
|
||||
}
|
||||
|
||||
var (
|
||||
NotDetectedError = errors.New("Charset not detected.")
|
||||
)
|
||||
|
||||
// DetectBest returns the Result with highest Confidence.
|
||||
func (d *Detector) DetectBest(b []byte) (r *Result, err error) {
|
||||
var all []Result
|
||||
if all, err = d.DetectAll(b); err == nil {
|
||||
r = &all[0]
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
// DetectAll returns all Results which have non-zero Confidence. The Results are sorted by Confidence in descending order.
|
||||
func (d *Detector) DetectAll(b []byte) ([]Result, error) {
|
||||
input := newRecognizerInput(b, d.stripTag)
|
||||
outputChan := make(chan recognizerOutput)
|
||||
for _, r := range d.recognizers {
|
||||
go matchHelper(r, input, outputChan)
|
||||
}
|
||||
outputs := make([]recognizerOutput, 0, len(d.recognizers))
|
||||
for i := 0; i < len(d.recognizers); i++ {
|
||||
o := <-outputChan
|
||||
if o.Confidence > 0 {
|
||||
outputs = append(outputs, o)
|
||||
}
|
||||
}
|
||||
if len(outputs) == 0 {
|
||||
return nil, NotDetectedError
|
||||
}
|
||||
|
||||
sort.Sort(recognizerOutputs(outputs))
|
||||
dedupOutputs := make([]Result, 0, len(outputs))
|
||||
foundCharsets := make(map[string]struct{}, len(outputs))
|
||||
for _, o := range outputs {
|
||||
if _, found := foundCharsets[o.Charset]; !found {
|
||||
dedupOutputs = append(dedupOutputs, Result(o))
|
||||
foundCharsets[o.Charset] = struct{}{}
|
||||
}
|
||||
}
|
||||
if len(dedupOutputs) == 0 {
|
||||
return nil, NotDetectedError
|
||||
}
|
||||
return dedupOutputs, nil
|
||||
}
|
||||
|
||||
func matchHelper(r recognizer, input *recognizerInput, outputChan chan<- recognizerOutput) {
|
||||
outputChan <- r.Match(input)
|
||||
}
|
||||
|
||||
type recognizerOutputs []recognizerOutput
|
||||
|
||||
func (r recognizerOutputs) Len() int { return len(r) }
|
||||
func (r recognizerOutputs) Less(i, j int) bool { return r[i].Confidence > r[j].Confidence }
|
||||
func (r recognizerOutputs) Swap(i, j int) { r[i], r[j] = r[j], r[i] }
|
||||
|
|
@ -1,51 +0,0 @@
|
|||
<html>
|
||||
|
||||
<head>
|
||||
<meta http-equiv="Content-Type" content="text/html; charset=us-ascii"></meta>
|
||||
<title>ICU License - ICU 1.8.1 and later</title>
|
||||
</head>
|
||||
|
||||
<body BGCOLOR="#ffffff">
|
||||
<h2>ICU License - ICU 1.8.1 and later</h2>
|
||||
|
||||
<p>COPYRIGHT AND PERMISSION NOTICE</p>
|
||||
|
||||
<p>
|
||||
Copyright (c) 1995-2012 International Business Machines Corporation and others
|
||||
</p>
|
||||
<p>
|
||||
All rights reserved.
|
||||
</p>
|
||||
<p>
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"),
|
||||
to deal in the Software without restriction, including without limitation
|
||||
the rights to use, copy, modify, merge, publish, distribute, and/or sell
|
||||
copies of the Software, and to permit persons
|
||||
to whom the Software is furnished to do so, provided that the above
|
||||
copyright notice(s) and this permission notice appear in all copies
|
||||
of the Software and that both the above copyright notice(s) and this
|
||||
permission notice appear in supporting documentation.
|
||||
</p>
|
||||
<p>
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR IMPLIED,
|
||||
INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY, FITNESS FOR A
|
||||
PARTICULAR PURPOSE AND NONINFRINGEMENT OF THIRD PARTY RIGHTS. IN NO EVENT SHALL
|
||||
THE COPYRIGHT HOLDER OR HOLDERS INCLUDED IN THIS NOTICE BE LIABLE FOR ANY CLAIM,
|
||||
OR ANY SPECIAL INDIRECT OR CONSEQUENTIAL DAMAGES, OR ANY DAMAGES WHATSOEVER
|
||||
RESULTING FROM LOSS OF USE, DATA OR PROFITS, WHETHER IN AN ACTION OF CONTRACT,
|
||||
NEGLIGENCE OR OTHER TORTIOUS ACTION, ARISING OUT OF OR IN CONNECTION WITH THE
|
||||
USE OR PERFORMANCE OF THIS SOFTWARE.
|
||||
</p>
|
||||
<p>
|
||||
Except as contained in this notice, the name of a copyright holder shall not be
|
||||
used in advertising or otherwise to promote the sale, use or other dealings in
|
||||
this Software without prior written authorization of the copyright holder.
|
||||
</p>
|
||||
|
||||
<hr>
|
||||
<p><small>
|
||||
All trademarks and registered trademarks mentioned herein are the property of their respective owners.
|
||||
</small></p>
|
||||
</body>
|
||||
</html>
|
||||
|
|
@ -1,345 +0,0 @@
|
|||
package chardet
|
||||
|
||||
import (
|
||||
"errors"
|
||||
"math"
|
||||
)
|
||||
|
||||
type recognizerMultiByte struct {
|
||||
charset string
|
||||
language string
|
||||
decoder charDecoder
|
||||
commonChars []uint16
|
||||
}
|
||||
|
||||
type charDecoder interface {
|
||||
DecodeOneChar([]byte) (c uint16, remain []byte, err error)
|
||||
}
|
||||
|
||||
func (r *recognizerMultiByte) Match(input *recognizerInput) (output recognizerOutput) {
|
||||
return recognizerOutput{
|
||||
Charset: r.charset,
|
||||
Language: r.language,
|
||||
Confidence: r.matchConfidence(input),
|
||||
}
|
||||
}
|
||||
|
||||
func (r *recognizerMultiByte) matchConfidence(input *recognizerInput) int {
|
||||
raw := input.raw
|
||||
var c uint16
|
||||
var err error
|
||||
var totalCharCount, badCharCount, singleByteCharCount, doubleByteCharCount, commonCharCount int
|
||||
for c, raw, err = r.decoder.DecodeOneChar(raw); len(raw) > 0; c, raw, err = r.decoder.DecodeOneChar(raw) {
|
||||
totalCharCount++
|
||||
if err != nil {
|
||||
badCharCount++
|
||||
} else if c <= 0xFF {
|
||||
singleByteCharCount++
|
||||
} else {
|
||||
doubleByteCharCount++
|
||||
if r.commonChars != nil && binarySearch(r.commonChars, c) {
|
||||
commonCharCount++
|
||||
}
|
||||
}
|
||||
if badCharCount >= 2 && badCharCount*5 >= doubleByteCharCount {
|
||||
return 0
|
||||
}
|
||||
}
|
||||
|
||||
if doubleByteCharCount <= 10 && badCharCount == 0 {
|
||||
if doubleByteCharCount == 0 && totalCharCount < 10 {
|
||||
return 0
|
||||
} else {
|
||||
return 10
|
||||
}
|
||||
}
|
||||
|
||||
if doubleByteCharCount < 20*badCharCount {
|
||||
return 0
|
||||
}
|
||||
if r.commonChars == nil {
|
||||
confidence := 30 + doubleByteCharCount - 20*badCharCount
|
||||
if confidence > 100 {
|
||||
confidence = 100
|
||||
}
|
||||
return confidence
|
||||
}
|
||||
maxVal := math.Log(float64(doubleByteCharCount) / 4)
|
||||
scaleFactor := 90 / maxVal
|
||||
confidence := int(math.Log(float64(commonCharCount)+1)*scaleFactor + 10)
|
||||
if confidence > 100 {
|
||||
confidence = 100
|
||||
}
|
||||
if confidence < 0 {
|
||||
confidence = 0
|
||||
}
|
||||
return confidence
|
||||
}
|
||||
|
||||
func binarySearch(l []uint16, c uint16) bool {
|
||||
start := 0
|
||||
end := len(l) - 1
|
||||
for start <= end {
|
||||
mid := (start + end) / 2
|
||||
if c == l[mid] {
|
||||
return true
|
||||
} else if c < l[mid] {
|
||||
end = mid - 1
|
||||
} else {
|
||||
start = mid + 1
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
var eobError = errors.New("End of input buffer")
|
||||
var badCharError = errors.New("Decode a bad char")
|
||||
|
||||
type charDecoder_sjis struct {
|
||||
}
|
||||
|
||||
func (charDecoder_sjis) DecodeOneChar(input []byte) (c uint16, remain []byte, err error) {
|
||||
if len(input) == 0 {
|
||||
return 0, nil, eobError
|
||||
}
|
||||
first := input[0]
|
||||
c = uint16(first)
|
||||
remain = input[1:]
|
||||
if first <= 0x7F || (first > 0xA0 && first <= 0xDF) {
|
||||
return
|
||||
}
|
||||
if len(remain) == 0 {
|
||||
return c, remain, badCharError
|
||||
}
|
||||
second := remain[0]
|
||||
remain = remain[1:]
|
||||
c = c<<8 | uint16(second)
|
||||
if (second >= 0x40 && second <= 0x7F) || (second >= 0x80 && second <= 0xFE) {
|
||||
} else {
|
||||
err = badCharError
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
var commonChars_sjis = []uint16{
|
||||
0x8140, 0x8141, 0x8142, 0x8145, 0x815b, 0x8169, 0x816a, 0x8175, 0x8176, 0x82a0,
|
||||
0x82a2, 0x82a4, 0x82a9, 0x82aa, 0x82ab, 0x82ad, 0x82af, 0x82b1, 0x82b3, 0x82b5,
|
||||
0x82b7, 0x82bd, 0x82be, 0x82c1, 0x82c4, 0x82c5, 0x82c6, 0x82c8, 0x82c9, 0x82cc,
|
||||
0x82cd, 0x82dc, 0x82e0, 0x82e7, 0x82e8, 0x82e9, 0x82ea, 0x82f0, 0x82f1, 0x8341,
|
||||
0x8343, 0x834e, 0x834f, 0x8358, 0x835e, 0x8362, 0x8367, 0x8375, 0x8376, 0x8389,
|
||||
0x838a, 0x838b, 0x838d, 0x8393, 0x8e96, 0x93fa, 0x95aa,
|
||||
}
|
||||
|
||||
func newRecognizer_sjis() *recognizerMultiByte {
|
||||
return &recognizerMultiByte{
|
||||
"Shift_JIS",
|
||||
"ja",
|
||||
charDecoder_sjis{},
|
||||
commonChars_sjis,
|
||||
}
|
||||
}
|
||||
|
||||
type charDecoder_euc struct {
|
||||
}
|
||||
|
||||
func (charDecoder_euc) DecodeOneChar(input []byte) (c uint16, remain []byte, err error) {
|
||||
if len(input) == 0 {
|
||||
return 0, nil, eobError
|
||||
}
|
||||
first := input[0]
|
||||
remain = input[1:]
|
||||
c = uint16(first)
|
||||
if first <= 0x8D {
|
||||
return uint16(first), remain, nil
|
||||
}
|
||||
if len(remain) == 0 {
|
||||
return 0, nil, eobError
|
||||
}
|
||||
second := remain[0]
|
||||
remain = remain[1:]
|
||||
c = c<<8 | uint16(second)
|
||||
if first >= 0xA1 && first <= 0xFE {
|
||||
if second < 0xA1 {
|
||||
err = badCharError
|
||||
}
|
||||
return
|
||||
}
|
||||
if first == 0x8E {
|
||||
if second < 0xA1 {
|
||||
err = badCharError
|
||||
}
|
||||
return
|
||||
}
|
||||
if first == 0x8F {
|
||||
if len(remain) == 0 {
|
||||
return 0, nil, eobError
|
||||
}
|
||||
third := remain[0]
|
||||
remain = remain[1:]
|
||||
c = c<<0 | uint16(third)
|
||||
if third < 0xa1 {
|
||||
err = badCharError
|
||||
}
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
var commonChars_euc_jp = []uint16{
|
||||
0xa1a1, 0xa1a2, 0xa1a3, 0xa1a6, 0xa1bc, 0xa1ca, 0xa1cb, 0xa1d6, 0xa1d7, 0xa4a2,
|
||||
0xa4a4, 0xa4a6, 0xa4a8, 0xa4aa, 0xa4ab, 0xa4ac, 0xa4ad, 0xa4af, 0xa4b1, 0xa4b3,
|
||||
0xa4b5, 0xa4b7, 0xa4b9, 0xa4bb, 0xa4bd, 0xa4bf, 0xa4c0, 0xa4c1, 0xa4c3, 0xa4c4,
|
||||
0xa4c6, 0xa4c7, 0xa4c8, 0xa4c9, 0xa4ca, 0xa4cb, 0xa4ce, 0xa4cf, 0xa4d0, 0xa4de,
|
||||
0xa4df, 0xa4e1, 0xa4e2, 0xa4e4, 0xa4e8, 0xa4e9, 0xa4ea, 0xa4eb, 0xa4ec, 0xa4ef,
|
||||
0xa4f2, 0xa4f3, 0xa5a2, 0xa5a3, 0xa5a4, 0xa5a6, 0xa5a7, 0xa5aa, 0xa5ad, 0xa5af,
|
||||
0xa5b0, 0xa5b3, 0xa5b5, 0xa5b7, 0xa5b8, 0xa5b9, 0xa5bf, 0xa5c3, 0xa5c6, 0xa5c7,
|
||||
0xa5c8, 0xa5c9, 0xa5cb, 0xa5d0, 0xa5d5, 0xa5d6, 0xa5d7, 0xa5de, 0xa5e0, 0xa5e1,
|
||||
0xa5e5, 0xa5e9, 0xa5ea, 0xa5eb, 0xa5ec, 0xa5ed, 0xa5f3, 0xb8a9, 0xb9d4, 0xbaee,
|
||||
0xbbc8, 0xbef0, 0xbfb7, 0xc4ea, 0xc6fc, 0xc7bd, 0xcab8, 0xcaf3, 0xcbdc, 0xcdd1,
|
||||
}
|
||||
|
||||
var commonChars_euc_kr = []uint16{
|
||||
0xb0a1, 0xb0b3, 0xb0c5, 0xb0cd, 0xb0d4, 0xb0e6, 0xb0ed, 0xb0f8, 0xb0fa, 0xb0fc,
|
||||
0xb1b8, 0xb1b9, 0xb1c7, 0xb1d7, 0xb1e2, 0xb3aa, 0xb3bb, 0xb4c2, 0xb4cf, 0xb4d9,
|
||||
0xb4eb, 0xb5a5, 0xb5b5, 0xb5bf, 0xb5c7, 0xb5e9, 0xb6f3, 0xb7af, 0xb7c2, 0xb7ce,
|
||||
0xb8a6, 0xb8ae, 0xb8b6, 0xb8b8, 0xb8bb, 0xb8e9, 0xb9ab, 0xb9ae, 0xb9cc, 0xb9ce,
|
||||
0xb9fd, 0xbab8, 0xbace, 0xbad0, 0xbaf1, 0xbbe7, 0xbbf3, 0xbbfd, 0xbcad, 0xbcba,
|
||||
0xbcd2, 0xbcf6, 0xbdba, 0xbdc0, 0xbdc3, 0xbdc5, 0xbec6, 0xbec8, 0xbedf, 0xbeee,
|
||||
0xbef8, 0xbefa, 0xbfa1, 0xbfa9, 0xbfc0, 0xbfe4, 0xbfeb, 0xbfec, 0xbff8, 0xc0a7,
|
||||
0xc0af, 0xc0b8, 0xc0ba, 0xc0bb, 0xc0bd, 0xc0c7, 0xc0cc, 0xc0ce, 0xc0cf, 0xc0d6,
|
||||
0xc0da, 0xc0e5, 0xc0fb, 0xc0fc, 0xc1a4, 0xc1a6, 0xc1b6, 0xc1d6, 0xc1df, 0xc1f6,
|
||||
0xc1f8, 0xc4a1, 0xc5cd, 0xc6ae, 0xc7cf, 0xc7d1, 0xc7d2, 0xc7d8, 0xc7e5, 0xc8ad,
|
||||
}
|
||||
|
||||
func newRecognizer_euc_jp() *recognizerMultiByte {
|
||||
return &recognizerMultiByte{
|
||||
"EUC-JP",
|
||||
"ja",
|
||||
charDecoder_euc{},
|
||||
commonChars_euc_jp,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_euc_kr() *recognizerMultiByte {
|
||||
return &recognizerMultiByte{
|
||||
"EUC-KR",
|
||||
"ko",
|
||||
charDecoder_euc{},
|
||||
commonChars_euc_kr,
|
||||
}
|
||||
}
|
||||
|
||||
type charDecoder_big5 struct {
|
||||
}
|
||||
|
||||
func (charDecoder_big5) DecodeOneChar(input []byte) (c uint16, remain []byte, err error) {
|
||||
if len(input) == 0 {
|
||||
return 0, nil, eobError
|
||||
}
|
||||
first := input[0]
|
||||
remain = input[1:]
|
||||
c = uint16(first)
|
||||
if first <= 0x7F || first == 0xFF {
|
||||
return
|
||||
}
|
||||
if len(remain) == 0 {
|
||||
return c, nil, eobError
|
||||
}
|
||||
second := remain[0]
|
||||
remain = remain[1:]
|
||||
c = c<<8 | uint16(second)
|
||||
if second < 0x40 || second == 0x7F || second == 0xFF {
|
||||
err = badCharError
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
var commonChars_big5 = []uint16{
|
||||
0xa140, 0xa141, 0xa142, 0xa143, 0xa147, 0xa149, 0xa175, 0xa176, 0xa440, 0xa446,
|
||||
0xa447, 0xa448, 0xa451, 0xa454, 0xa457, 0xa464, 0xa46a, 0xa46c, 0xa477, 0xa4a3,
|
||||
0xa4a4, 0xa4a7, 0xa4c1, 0xa4ce, 0xa4d1, 0xa4df, 0xa4e8, 0xa4fd, 0xa540, 0xa548,
|
||||
0xa558, 0xa569, 0xa5cd, 0xa5e7, 0xa657, 0xa661, 0xa662, 0xa668, 0xa670, 0xa6a8,
|
||||
0xa6b3, 0xa6b9, 0xa6d3, 0xa6db, 0xa6e6, 0xa6f2, 0xa740, 0xa751, 0xa759, 0xa7da,
|
||||
0xa8a3, 0xa8a5, 0xa8ad, 0xa8d1, 0xa8d3, 0xa8e4, 0xa8fc, 0xa9c0, 0xa9d2, 0xa9f3,
|
||||
0xaa6b, 0xaaba, 0xaabe, 0xaacc, 0xaafc, 0xac47, 0xac4f, 0xacb0, 0xacd2, 0xad59,
|
||||
0xaec9, 0xafe0, 0xb0ea, 0xb16f, 0xb2b3, 0xb2c4, 0xb36f, 0xb44c, 0xb44e, 0xb54c,
|
||||
0xb5a5, 0xb5bd, 0xb5d0, 0xb5d8, 0xb671, 0xb7ed, 0xb867, 0xb944, 0xbad8, 0xbb44,
|
||||
0xbba1, 0xbdd1, 0xc2c4, 0xc3b9, 0xc440, 0xc45f,
|
||||
}
|
||||
|
||||
func newRecognizer_big5() *recognizerMultiByte {
|
||||
return &recognizerMultiByte{
|
||||
"Big5",
|
||||
"zh",
|
||||
charDecoder_big5{},
|
||||
commonChars_big5,
|
||||
}
|
||||
}
|
||||
|
||||
type charDecoder_gb_18030 struct {
|
||||
}
|
||||
|
||||
func (charDecoder_gb_18030) DecodeOneChar(input []byte) (c uint16, remain []byte, err error) {
|
||||
if len(input) == 0 {
|
||||
return 0, nil, eobError
|
||||
}
|
||||
first := input[0]
|
||||
remain = input[1:]
|
||||
c = uint16(first)
|
||||
if first <= 0x80 {
|
||||
return
|
||||
}
|
||||
if len(remain) == 0 {
|
||||
return 0, nil, eobError
|
||||
}
|
||||
second := remain[0]
|
||||
remain = remain[1:]
|
||||
c = c<<8 | uint16(second)
|
||||
if first >= 0x81 && first <= 0xFE {
|
||||
if (second >= 0x40 && second <= 0x7E) || (second >= 0x80 && second <= 0xFE) {
|
||||
return
|
||||
}
|
||||
|
||||
if second >= 0x30 && second <= 0x39 {
|
||||
if len(remain) == 0 {
|
||||
return 0, nil, eobError
|
||||
}
|
||||
third := remain[0]
|
||||
remain = remain[1:]
|
||||
if third >= 0x81 && third <= 0xFE {
|
||||
if len(remain) == 0 {
|
||||
return 0, nil, eobError
|
||||
}
|
||||
fourth := remain[0]
|
||||
remain = remain[1:]
|
||||
if fourth >= 0x30 && fourth <= 0x39 {
|
||||
c = c<<16 | uint16(third)<<8 | uint16(fourth)
|
||||
return
|
||||
}
|
||||
}
|
||||
}
|
||||
err = badCharError
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
var commonChars_gb_18030 = []uint16{
|
||||
0xa1a1, 0xa1a2, 0xa1a3, 0xa1a4, 0xa1b0, 0xa1b1, 0xa1f1, 0xa1f3, 0xa3a1, 0xa3ac,
|
||||
0xa3ba, 0xb1a8, 0xb1b8, 0xb1be, 0xb2bb, 0xb3c9, 0xb3f6, 0xb4f3, 0xb5bd, 0xb5c4,
|
||||
0xb5e3, 0xb6af, 0xb6d4, 0xb6e0, 0xb7a2, 0xb7a8, 0xb7bd, 0xb7d6, 0xb7dd, 0xb8b4,
|
||||
0xb8df, 0xb8f6, 0xb9ab, 0xb9c9, 0xb9d8, 0xb9fa, 0xb9fd, 0xbacd, 0xbba7, 0xbbd6,
|
||||
0xbbe1, 0xbbfa, 0xbcbc, 0xbcdb, 0xbcfe, 0xbdcc, 0xbecd, 0xbedd, 0xbfb4, 0xbfc6,
|
||||
0xbfc9, 0xc0b4, 0xc0ed, 0xc1cb, 0xc2db, 0xc3c7, 0xc4dc, 0xc4ea, 0xc5cc, 0xc6f7,
|
||||
0xc7f8, 0xc8ab, 0xc8cb, 0xc8d5, 0xc8e7, 0xc9cf, 0xc9fa, 0xcab1, 0xcab5, 0xcac7,
|
||||
0xcad0, 0xcad6, 0xcaf5, 0xcafd, 0xccec, 0xcdf8, 0xceaa, 0xcec4, 0xced2, 0xcee5,
|
||||
0xcfb5, 0xcfc2, 0xcfd6, 0xd0c2, 0xd0c5, 0xd0d0, 0xd0d4, 0xd1a7, 0xd2aa, 0xd2b2,
|
||||
0xd2b5, 0xd2bb, 0xd2d4, 0xd3c3, 0xd3d0, 0xd3fd, 0xd4c2, 0xd4da, 0xd5e2, 0xd6d0,
|
||||
}
|
||||
|
||||
func newRecognizer_gb_18030() *recognizerMultiByte {
|
||||
return &recognizerMultiByte{
|
||||
"GB-18030",
|
||||
"zh",
|
||||
charDecoder_gb_18030{},
|
||||
commonChars_gb_18030,
|
||||
}
|
||||
}
|
||||
|
|
@ -1,83 +0,0 @@
|
|||
package chardet
|
||||
|
||||
type recognizer interface {
|
||||
Match(*recognizerInput) recognizerOutput
|
||||
}
|
||||
|
||||
type recognizerOutput Result
|
||||
|
||||
type recognizerInput struct {
|
||||
raw []byte
|
||||
input []byte
|
||||
tagStripped bool
|
||||
byteStats []int
|
||||
hasC1Bytes bool
|
||||
}
|
||||
|
||||
func newRecognizerInput(raw []byte, stripTag bool) *recognizerInput {
|
||||
input, stripped := mayStripInput(raw, stripTag)
|
||||
byteStats := computeByteStats(input)
|
||||
return &recognizerInput{
|
||||
raw: raw,
|
||||
input: input,
|
||||
tagStripped: stripped,
|
||||
byteStats: byteStats,
|
||||
hasC1Bytes: computeHasC1Bytes(byteStats),
|
||||
}
|
||||
}
|
||||
|
||||
func mayStripInput(raw []byte, stripTag bool) (out []byte, stripped bool) {
|
||||
const inputBufferSize = 8192
|
||||
out = make([]byte, 0, inputBufferSize)
|
||||
var badTags, openTags int32
|
||||
var inMarkup bool = false
|
||||
stripped = false
|
||||
if stripTag {
|
||||
stripped = true
|
||||
for _, c := range raw {
|
||||
if c == '<' {
|
||||
if inMarkup {
|
||||
badTags += 1
|
||||
}
|
||||
inMarkup = true
|
||||
openTags += 1
|
||||
}
|
||||
if !inMarkup {
|
||||
out = append(out, c)
|
||||
if len(out) >= inputBufferSize {
|
||||
break
|
||||
}
|
||||
}
|
||||
if c == '>' {
|
||||
inMarkup = false
|
||||
}
|
||||
}
|
||||
}
|
||||
if openTags < 5 || openTags/5 < badTags || (len(out) < 100 && len(raw) > 600) {
|
||||
limit := len(raw)
|
||||
if limit > inputBufferSize {
|
||||
limit = inputBufferSize
|
||||
}
|
||||
out = make([]byte, limit)
|
||||
copy(out, raw[:limit])
|
||||
stripped = false
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
func computeByteStats(input []byte) []int {
|
||||
r := make([]int, 256)
|
||||
for _, c := range input {
|
||||
r[c] += 1
|
||||
}
|
||||
return r
|
||||
}
|
||||
|
||||
func computeHasC1Bytes(byteStats []int) bool {
|
||||
for _, count := range byteStats[0x80 : 0x9F+1] {
|
||||
if count > 0 {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
|
@ -1,882 +0,0 @@
|
|||
package chardet
|
||||
|
||||
// Recognizer for single byte charset family
|
||||
type recognizerSingleByte struct {
|
||||
charset string
|
||||
hasC1ByteCharset string
|
||||
language string
|
||||
charMap *[256]byte
|
||||
ngram *[64]uint32
|
||||
}
|
||||
|
||||
func (r *recognizerSingleByte) Match(input *recognizerInput) recognizerOutput {
|
||||
var charset string = r.charset
|
||||
if input.hasC1Bytes && len(r.hasC1ByteCharset) > 0 {
|
||||
charset = r.hasC1ByteCharset
|
||||
}
|
||||
return recognizerOutput{
|
||||
Charset: charset,
|
||||
Language: r.language,
|
||||
Confidence: r.parseNgram(input.input),
|
||||
}
|
||||
}
|
||||
|
||||
type ngramState struct {
|
||||
ngram uint32
|
||||
ignoreSpace bool
|
||||
ngramCount, ngramHit uint32
|
||||
table *[64]uint32
|
||||
}
|
||||
|
||||
func newNgramState(table *[64]uint32) *ngramState {
|
||||
return &ngramState{
|
||||
ngram: 0,
|
||||
ignoreSpace: false,
|
||||
ngramCount: 0,
|
||||
ngramHit: 0,
|
||||
table: table,
|
||||
}
|
||||
}
|
||||
|
||||
func (s *ngramState) AddByte(b byte) {
|
||||
const ngramMask = 0xFFFFFF
|
||||
if !(b == 0x20 && s.ignoreSpace) {
|
||||
s.ngram = ((s.ngram << 8) | uint32(b)) & ngramMask
|
||||
s.ignoreSpace = (s.ngram == 0x20)
|
||||
s.ngramCount++
|
||||
if s.lookup() {
|
||||
s.ngramHit++
|
||||
}
|
||||
}
|
||||
s.ignoreSpace = (b == 0x20)
|
||||
}
|
||||
|
||||
func (s *ngramState) HitRate() float32 {
|
||||
if s.ngramCount == 0 {
|
||||
return 0
|
||||
}
|
||||
return float32(s.ngramHit) / float32(s.ngramCount)
|
||||
}
|
||||
|
||||
func (s *ngramState) lookup() bool {
|
||||
var index int
|
||||
if s.table[index+32] <= s.ngram {
|
||||
index += 32
|
||||
}
|
||||
if s.table[index+16] <= s.ngram {
|
||||
index += 16
|
||||
}
|
||||
if s.table[index+8] <= s.ngram {
|
||||
index += 8
|
||||
}
|
||||
if s.table[index+4] <= s.ngram {
|
||||
index += 4
|
||||
}
|
||||
if s.table[index+2] <= s.ngram {
|
||||
index += 2
|
||||
}
|
||||
if s.table[index+1] <= s.ngram {
|
||||
index += 1
|
||||
}
|
||||
if s.table[index] > s.ngram {
|
||||
index -= 1
|
||||
}
|
||||
if index < 0 || s.table[index] != s.ngram {
|
||||
return false
|
||||
}
|
||||
return true
|
||||
}
|
||||
|
||||
func (r *recognizerSingleByte) parseNgram(input []byte) int {
|
||||
state := newNgramState(r.ngram)
|
||||
for _, inChar := range input {
|
||||
c := r.charMap[inChar]
|
||||
if c != 0 {
|
||||
state.AddByte(c)
|
||||
}
|
||||
}
|
||||
state.AddByte(0x20)
|
||||
rate := state.HitRate()
|
||||
if rate > 0.33 {
|
||||
return 98
|
||||
}
|
||||
return int(rate * 300)
|
||||
}
|
||||
|
||||
var charMap_8859_1 = [256]byte{
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x00,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0xAA, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0xB5, 0x20, 0x20,
|
||||
0x20, 0x20, 0xBA, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0x20,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xDF,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0x20,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF,
|
||||
}
|
||||
|
||||
var ngrams_8859_1_en = [64]uint32{
|
||||
0x206120, 0x20616E, 0x206265, 0x20636F, 0x20666F, 0x206861, 0x206865, 0x20696E, 0x206D61, 0x206F66, 0x207072, 0x207265, 0x207361, 0x207374, 0x207468, 0x20746F,
|
||||
0x207768, 0x616964, 0x616C20, 0x616E20, 0x616E64, 0x617320, 0x617420, 0x617465, 0x617469, 0x642061, 0x642074, 0x652061, 0x652073, 0x652074, 0x656420, 0x656E74,
|
||||
0x657220, 0x657320, 0x666F72, 0x686174, 0x686520, 0x686572, 0x696420, 0x696E20, 0x696E67, 0x696F6E, 0x697320, 0x6E2061, 0x6E2074, 0x6E6420, 0x6E6720, 0x6E7420,
|
||||
0x6F6620, 0x6F6E20, 0x6F7220, 0x726520, 0x727320, 0x732061, 0x732074, 0x736169, 0x737420, 0x742074, 0x746572, 0x746861, 0x746865, 0x74696F, 0x746F20, 0x747320,
|
||||
}
|
||||
|
||||
var ngrams_8859_1_da = [64]uint32{
|
||||
0x206166, 0x206174, 0x206465, 0x20656E, 0x206572, 0x20666F, 0x206861, 0x206920, 0x206D65, 0x206F67, 0x2070E5, 0x207369, 0x207374, 0x207469, 0x207669, 0x616620,
|
||||
0x616E20, 0x616E64, 0x617220, 0x617420, 0x646520, 0x64656E, 0x646572, 0x646574, 0x652073, 0x656420, 0x656465, 0x656E20, 0x656E64, 0x657220, 0x657265, 0x657320,
|
||||
0x657420, 0x666F72, 0x676520, 0x67656E, 0x676572, 0x696765, 0x696C20, 0x696E67, 0x6B6520, 0x6B6B65, 0x6C6572, 0x6C6967, 0x6C6C65, 0x6D6564, 0x6E6465, 0x6E6520,
|
||||
0x6E6720, 0x6E6765, 0x6F6720, 0x6F6D20, 0x6F7220, 0x70E520, 0x722064, 0x722065, 0x722073, 0x726520, 0x737465, 0x742073, 0x746520, 0x746572, 0x74696C, 0x766572,
|
||||
}
|
||||
|
||||
var ngrams_8859_1_de = [64]uint32{
|
||||
0x20616E, 0x206175, 0x206265, 0x206461, 0x206465, 0x206469, 0x206569, 0x206765, 0x206861, 0x20696E, 0x206D69, 0x207363, 0x207365, 0x20756E, 0x207665, 0x20766F,
|
||||
0x207765, 0x207A75, 0x626572, 0x636820, 0x636865, 0x636874, 0x646173, 0x64656E, 0x646572, 0x646965, 0x652064, 0x652073, 0x65696E, 0x656974, 0x656E20, 0x657220,
|
||||
0x657320, 0x67656E, 0x68656E, 0x687420, 0x696368, 0x696520, 0x696E20, 0x696E65, 0x697420, 0x6C6963, 0x6C6C65, 0x6E2061, 0x6E2064, 0x6E2073, 0x6E6420, 0x6E6465,
|
||||
0x6E6520, 0x6E6720, 0x6E6765, 0x6E7465, 0x722064, 0x726465, 0x726569, 0x736368, 0x737465, 0x742064, 0x746520, 0x74656E, 0x746572, 0x756E64, 0x756E67, 0x766572,
|
||||
}
|
||||
|
||||
var ngrams_8859_1_es = [64]uint32{
|
||||
0x206120, 0x206361, 0x20636F, 0x206465, 0x20656C, 0x20656E, 0x206573, 0x20696E, 0x206C61, 0x206C6F, 0x207061, 0x20706F, 0x207072, 0x207175, 0x207265, 0x207365,
|
||||
0x20756E, 0x207920, 0x612063, 0x612064, 0x612065, 0x61206C, 0x612070, 0x616369, 0x61646F, 0x616C20, 0x617220, 0x617320, 0x6369F3, 0x636F6E, 0x646520, 0x64656C,
|
||||
0x646F20, 0x652064, 0x652065, 0x65206C, 0x656C20, 0x656E20, 0x656E74, 0x657320, 0x657374, 0x69656E, 0x69F36E, 0x6C6120, 0x6C6F73, 0x6E2065, 0x6E7465, 0x6F2064,
|
||||
0x6F2065, 0x6F6E20, 0x6F7220, 0x6F7320, 0x706172, 0x717565, 0x726120, 0x726573, 0x732064, 0x732065, 0x732070, 0x736520, 0x746520, 0x746F20, 0x756520, 0xF36E20,
|
||||
}
|
||||
|
||||
var ngrams_8859_1_fr = [64]uint32{
|
||||
0x206175, 0x20636F, 0x206461, 0x206465, 0x206475, 0x20656E, 0x206574, 0x206C61, 0x206C65, 0x207061, 0x20706F, 0x207072, 0x207175, 0x207365, 0x20736F, 0x20756E,
|
||||
0x20E020, 0x616E74, 0x617469, 0x636520, 0x636F6E, 0x646520, 0x646573, 0x647520, 0x652061, 0x652063, 0x652064, 0x652065, 0x65206C, 0x652070, 0x652073, 0x656E20,
|
||||
0x656E74, 0x657220, 0x657320, 0x657420, 0x657572, 0x696F6E, 0x697320, 0x697420, 0x6C6120, 0x6C6520, 0x6C6573, 0x6D656E, 0x6E2064, 0x6E6520, 0x6E7320, 0x6E7420,
|
||||
0x6F6E20, 0x6F6E74, 0x6F7572, 0x717565, 0x72206C, 0x726520, 0x732061, 0x732064, 0x732065, 0x73206C, 0x732070, 0x742064, 0x746520, 0x74696F, 0x756520, 0x757220,
|
||||
}
|
||||
|
||||
var ngrams_8859_1_it = [64]uint32{
|
||||
0x20616C, 0x206368, 0x20636F, 0x206465, 0x206469, 0x206520, 0x20696C, 0x20696E, 0x206C61, 0x207065, 0x207072, 0x20756E, 0x612063, 0x612064, 0x612070, 0x612073,
|
||||
0x61746F, 0x636865, 0x636F6E, 0x64656C, 0x646920, 0x652061, 0x652063, 0x652064, 0x652069, 0x65206C, 0x652070, 0x652073, 0x656C20, 0x656C6C, 0x656E74, 0x657220,
|
||||
0x686520, 0x692061, 0x692063, 0x692064, 0x692073, 0x696120, 0x696C20, 0x696E20, 0x696F6E, 0x6C6120, 0x6C6520, 0x6C6920, 0x6C6C61, 0x6E6520, 0x6E6920, 0x6E6F20,
|
||||
0x6E7465, 0x6F2061, 0x6F2064, 0x6F2069, 0x6F2073, 0x6F6E20, 0x6F6E65, 0x706572, 0x726120, 0x726520, 0x736920, 0x746120, 0x746520, 0x746920, 0x746F20, 0x7A696F,
|
||||
}
|
||||
|
||||
var ngrams_8859_1_nl = [64]uint32{
|
||||
0x20616C, 0x206265, 0x206461, 0x206465, 0x206469, 0x206565, 0x20656E, 0x206765, 0x206865, 0x20696E, 0x206D61, 0x206D65, 0x206F70, 0x207465, 0x207661, 0x207665,
|
||||
0x20766F, 0x207765, 0x207A69, 0x61616E, 0x616172, 0x616E20, 0x616E64, 0x617220, 0x617420, 0x636874, 0x646520, 0x64656E, 0x646572, 0x652062, 0x652076, 0x65656E,
|
||||
0x656572, 0x656E20, 0x657220, 0x657273, 0x657420, 0x67656E, 0x686574, 0x696520, 0x696E20, 0x696E67, 0x697320, 0x6E2062, 0x6E2064, 0x6E2065, 0x6E2068, 0x6E206F,
|
||||
0x6E2076, 0x6E6465, 0x6E6720, 0x6F6E64, 0x6F6F72, 0x6F7020, 0x6F7220, 0x736368, 0x737465, 0x742064, 0x746520, 0x74656E, 0x746572, 0x76616E, 0x766572, 0x766F6F,
|
||||
}
|
||||
|
||||
var ngrams_8859_1_no = [64]uint32{
|
||||
0x206174, 0x206176, 0x206465, 0x20656E, 0x206572, 0x20666F, 0x206861, 0x206920, 0x206D65, 0x206F67, 0x2070E5, 0x207365, 0x20736B, 0x20736F, 0x207374, 0x207469,
|
||||
0x207669, 0x20E520, 0x616E64, 0x617220, 0x617420, 0x646520, 0x64656E, 0x646574, 0x652073, 0x656420, 0x656E20, 0x656E65, 0x657220, 0x657265, 0x657420, 0x657474,
|
||||
0x666F72, 0x67656E, 0x696B6B, 0x696C20, 0x696E67, 0x6B6520, 0x6B6B65, 0x6C6520, 0x6C6C65, 0x6D6564, 0x6D656E, 0x6E2073, 0x6E6520, 0x6E6720, 0x6E6765, 0x6E6E65,
|
||||
0x6F6720, 0x6F6D20, 0x6F7220, 0x70E520, 0x722073, 0x726520, 0x736F6D, 0x737465, 0x742073, 0x746520, 0x74656E, 0x746572, 0x74696C, 0x747420, 0x747465, 0x766572,
|
||||
}
|
||||
|
||||
var ngrams_8859_1_pt = [64]uint32{
|
||||
0x206120, 0x20636F, 0x206461, 0x206465, 0x20646F, 0x206520, 0x206573, 0x206D61, 0x206E6F, 0x206F20, 0x207061, 0x20706F, 0x207072, 0x207175, 0x207265, 0x207365,
|
||||
0x20756D, 0x612061, 0x612063, 0x612064, 0x612070, 0x616465, 0x61646F, 0x616C20, 0x617220, 0x617261, 0x617320, 0x636F6D, 0x636F6E, 0x646120, 0x646520, 0x646F20,
|
||||
0x646F73, 0x652061, 0x652064, 0x656D20, 0x656E74, 0x657320, 0x657374, 0x696120, 0x696361, 0x6D656E, 0x6E7465, 0x6E746F, 0x6F2061, 0x6F2063, 0x6F2064, 0x6F2065,
|
||||
0x6F2070, 0x6F7320, 0x706172, 0x717565, 0x726120, 0x726573, 0x732061, 0x732064, 0x732065, 0x732070, 0x737461, 0x746520, 0x746F20, 0x756520, 0xE36F20, 0xE7E36F,
|
||||
}
|
||||
|
||||
var ngrams_8859_1_sv = [64]uint32{
|
||||
0x206174, 0x206176, 0x206465, 0x20656E, 0x2066F6, 0x206861, 0x206920, 0x20696E, 0x206B6F, 0x206D65, 0x206F63, 0x2070E5, 0x20736B, 0x20736F, 0x207374, 0x207469,
|
||||
0x207661, 0x207669, 0x20E472, 0x616465, 0x616E20, 0x616E64, 0x617220, 0x617474, 0x636820, 0x646520, 0x64656E, 0x646572, 0x646574, 0x656420, 0x656E20, 0x657220,
|
||||
0x657420, 0x66F672, 0x67656E, 0x696C6C, 0x696E67, 0x6B6120, 0x6C6C20, 0x6D6564, 0x6E2073, 0x6E6120, 0x6E6465, 0x6E6720, 0x6E6765, 0x6E696E, 0x6F6368, 0x6F6D20,
|
||||
0x6F6E20, 0x70E520, 0x722061, 0x722073, 0x726120, 0x736B61, 0x736F6D, 0x742073, 0x746120, 0x746520, 0x746572, 0x74696C, 0x747420, 0x766172, 0xE47220, 0xF67220,
|
||||
}
|
||||
|
||||
func newRecognizer_8859_1(language string, ngram *[64]uint32) *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: "ISO-8859-1",
|
||||
hasC1ByteCharset: "windows-1252",
|
||||
language: language,
|
||||
charMap: &charMap_8859_1,
|
||||
ngram: ngram,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_8859_1_en() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("en", &ngrams_8859_1_en)
|
||||
}
|
||||
func newRecognizer_8859_1_da() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("da", &ngrams_8859_1_da)
|
||||
}
|
||||
func newRecognizer_8859_1_de() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("de", &ngrams_8859_1_de)
|
||||
}
|
||||
func newRecognizer_8859_1_es() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("es", &ngrams_8859_1_es)
|
||||
}
|
||||
func newRecognizer_8859_1_fr() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("fr", &ngrams_8859_1_fr)
|
||||
}
|
||||
func newRecognizer_8859_1_it() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("it", &ngrams_8859_1_it)
|
||||
}
|
||||
func newRecognizer_8859_1_nl() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("nl", &ngrams_8859_1_nl)
|
||||
}
|
||||
func newRecognizer_8859_1_no() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("no", &ngrams_8859_1_no)
|
||||
}
|
||||
func newRecognizer_8859_1_pt() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("pt", &ngrams_8859_1_pt)
|
||||
}
|
||||
func newRecognizer_8859_1_sv() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("sv", &ngrams_8859_1_sv)
|
||||
}
|
||||
|
||||
var charMap_8859_2 = [256]byte{
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x00,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0xB1, 0x20, 0xB3, 0x20, 0xB5, 0xB6, 0x20,
|
||||
0x20, 0xB9, 0xBA, 0xBB, 0xBC, 0x20, 0xBE, 0xBF,
|
||||
0x20, 0xB1, 0x20, 0xB3, 0x20, 0xB5, 0xB6, 0xB7,
|
||||
0x20, 0xB9, 0xBA, 0xBB, 0xBC, 0x20, 0xBE, 0xBF,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0x20,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xDF,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0x20,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0x20,
|
||||
}
|
||||
|
||||
var ngrams_8859_2_cs = [64]uint32{
|
||||
0x206120, 0x206279, 0x20646F, 0x206A65, 0x206E61, 0x206E65, 0x206F20, 0x206F64, 0x20706F, 0x207072, 0x2070F8, 0x20726F, 0x207365, 0x20736F, 0x207374, 0x20746F,
|
||||
0x207620, 0x207679, 0x207A61, 0x612070, 0x636520, 0x636820, 0x652070, 0x652073, 0x652076, 0x656D20, 0x656EED, 0x686F20, 0x686F64, 0x697374, 0x6A6520, 0x6B7465,
|
||||
0x6C6520, 0x6C6920, 0x6E6120, 0x6EE920, 0x6EEC20, 0x6EED20, 0x6F2070, 0x6F646E, 0x6F6A69, 0x6F7374, 0x6F7520, 0x6F7661, 0x706F64, 0x706F6A, 0x70726F, 0x70F865,
|
||||
0x736520, 0x736F75, 0x737461, 0x737469, 0x73746E, 0x746572, 0x746EED, 0x746F20, 0x752070, 0xBE6520, 0xE16EED, 0xE9686F, 0xED2070, 0xED2073, 0xED6D20, 0xF86564,
|
||||
}
|
||||
|
||||
var ngrams_8859_2_hu = [64]uint32{
|
||||
0x206120, 0x20617A, 0x206265, 0x206567, 0x20656C, 0x206665, 0x206861, 0x20686F, 0x206973, 0x206B65, 0x206B69, 0x206BF6, 0x206C65, 0x206D61, 0x206D65, 0x206D69,
|
||||
0x206E65, 0x20737A, 0x207465, 0x20E973, 0x612061, 0x61206B, 0x61206D, 0x612073, 0x616B20, 0x616E20, 0x617A20, 0x62616E, 0x62656E, 0x656779, 0x656B20, 0x656C20,
|
||||
0x656C65, 0x656D20, 0x656E20, 0x657265, 0x657420, 0x657465, 0x657474, 0x677920, 0x686F67, 0x696E74, 0x697320, 0x6B2061, 0x6BF67A, 0x6D6567, 0x6D696E, 0x6E2061,
|
||||
0x6E616B, 0x6E656B, 0x6E656D, 0x6E7420, 0x6F6779, 0x732061, 0x737A65, 0x737A74, 0x737AE1, 0x73E967, 0x742061, 0x747420, 0x74E173, 0x7A6572, 0xE16E20, 0xE97320,
|
||||
}
|
||||
|
||||
var ngrams_8859_2_pl = [64]uint32{
|
||||
0x20637A, 0x20646F, 0x206920, 0x206A65, 0x206B6F, 0x206D61, 0x206D69, 0x206E61, 0x206E69, 0x206F64, 0x20706F, 0x207072, 0x207369, 0x207720, 0x207769, 0x207779,
|
||||
0x207A20, 0x207A61, 0x612070, 0x612077, 0x616E69, 0x636820, 0x637A65, 0x637A79, 0x646F20, 0x647A69, 0x652070, 0x652073, 0x652077, 0x65207A, 0x65676F, 0x656A20,
|
||||
0x656D20, 0x656E69, 0x676F20, 0x696120, 0x696520, 0x69656A, 0x6B6120, 0x6B6920, 0x6B6965, 0x6D6965, 0x6E6120, 0x6E6961, 0x6E6965, 0x6F2070, 0x6F7761, 0x6F7769,
|
||||
0x706F6C, 0x707261, 0x70726F, 0x70727A, 0x727A65, 0x727A79, 0x7369EA, 0x736B69, 0x737461, 0x776965, 0x796368, 0x796D20, 0x7A6520, 0x7A6965, 0x7A7920, 0xF37720,
|
||||
}
|
||||
|
||||
var ngrams_8859_2_ro = [64]uint32{
|
||||
0x206120, 0x206163, 0x206361, 0x206365, 0x20636F, 0x206375, 0x206465, 0x206469, 0x206C61, 0x206D61, 0x207065, 0x207072, 0x207365, 0x2073E3, 0x20756E, 0x20BA69,
|
||||
0x20EE6E, 0x612063, 0x612064, 0x617265, 0x617420, 0x617465, 0x617520, 0x636172, 0x636F6E, 0x637520, 0x63E320, 0x646520, 0x652061, 0x652063, 0x652064, 0x652070,
|
||||
0x652073, 0x656120, 0x656920, 0x656C65, 0x656E74, 0x657374, 0x692061, 0x692063, 0x692064, 0x692070, 0x696520, 0x696920, 0x696E20, 0x6C6120, 0x6C6520, 0x6C6F72,
|
||||
0x6C7569, 0x6E6520, 0x6E7472, 0x6F7220, 0x70656E, 0x726520, 0x726561, 0x727520, 0x73E320, 0x746520, 0x747275, 0x74E320, 0x756920, 0x756C20, 0xBA6920, 0xEE6E20,
|
||||
}
|
||||
|
||||
func newRecognizer_8859_2(language string, ngram *[64]uint32) *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: "ISO-8859-2",
|
||||
hasC1ByteCharset: "windows-1250",
|
||||
language: language,
|
||||
charMap: &charMap_8859_2,
|
||||
ngram: ngram,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_8859_2_cs() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("cs", &ngrams_8859_2_cs)
|
||||
}
|
||||
func newRecognizer_8859_2_hu() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("hu", &ngrams_8859_2_hu)
|
||||
}
|
||||
func newRecognizer_8859_2_pl() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("pl", &ngrams_8859_2_pl)
|
||||
}
|
||||
func newRecognizer_8859_2_ro() *recognizerSingleByte {
|
||||
return newRecognizer_8859_1("ro", &ngrams_8859_2_ro)
|
||||
}
|
||||
|
||||
var charMap_8859_5 = [256]byte{
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x00,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0x20, 0xFE, 0xFF,
|
||||
0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7,
|
||||
0xD8, 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7,
|
||||
0xD8, 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0x20, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0x20, 0xFE, 0xFF,
|
||||
}
|
||||
|
||||
var ngrams_8859_5_ru = [64]uint32{
|
||||
0x20D220, 0x20D2DE, 0x20D4DE, 0x20D7D0, 0x20D820, 0x20DAD0, 0x20DADE, 0x20DDD0, 0x20DDD5, 0x20DED1, 0x20DFDE, 0x20DFE0, 0x20E0D0, 0x20E1DE, 0x20E1E2, 0x20E2DE,
|
||||
0x20E7E2, 0x20EDE2, 0xD0DDD8, 0xD0E2EC, 0xD3DE20, 0xD5DBEC, 0xD5DDD8, 0xD5E1E2, 0xD5E220, 0xD820DF, 0xD8D520, 0xD8D820, 0xD8EF20, 0xDBD5DD, 0xDBD820, 0xDBECDD,
|
||||
0xDDD020, 0xDDD520, 0xDDD8D5, 0xDDD8EF, 0xDDDE20, 0xDDDED2, 0xDE20D2, 0xDE20DF, 0xDE20E1, 0xDED220, 0xDED2D0, 0xDED3DE, 0xDED920, 0xDEDBEC, 0xDEDC20, 0xDEE1E2,
|
||||
0xDFDEDB, 0xDFE0D5, 0xDFE0D8, 0xDFE0DE, 0xE0D0D2, 0xE0D5D4, 0xE1E2D0, 0xE1E2D2, 0xE1E2D8, 0xE1EF20, 0xE2D5DB, 0xE2DE20, 0xE2DEE0, 0xE2EC20, 0xE7E2DE, 0xEBE520,
|
||||
}
|
||||
|
||||
func newRecognizer_8859_5(language string, ngram *[64]uint32) *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: "ISO-8859-5",
|
||||
language: language,
|
||||
charMap: &charMap_8859_5,
|
||||
ngram: ngram,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_8859_5_ru() *recognizerSingleByte {
|
||||
return newRecognizer_8859_5("ru", &ngrams_8859_5_ru)
|
||||
}
|
||||
|
||||
var charMap_8859_6 = [256]byte{
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x00,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7,
|
||||
0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF,
|
||||
0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7,
|
||||
0xD8, 0xD9, 0xDA, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
}
|
||||
|
||||
var ngrams_8859_6_ar = [64]uint32{
|
||||
0x20C7E4, 0x20C7E6, 0x20C8C7, 0x20D9E4, 0x20E1EA, 0x20E4E4, 0x20E5E6, 0x20E8C7, 0xC720C7, 0xC7C120, 0xC7CA20, 0xC7D120, 0xC7E420, 0xC7E4C3, 0xC7E4C7, 0xC7E4C8,
|
||||
0xC7E4CA, 0xC7E4CC, 0xC7E4CD, 0xC7E4CF, 0xC7E4D3, 0xC7E4D9, 0xC7E4E2, 0xC7E4E5, 0xC7E4E8, 0xC7E4EA, 0xC7E520, 0xC7E620, 0xC7E6CA, 0xC820C7, 0xC920C7, 0xC920E1,
|
||||
0xC920E4, 0xC920E5, 0xC920E8, 0xCA20C7, 0xCF20C7, 0xCFC920, 0xD120C7, 0xD1C920, 0xD320C7, 0xD920C7, 0xD9E4E9, 0xE1EA20, 0xE420C7, 0xE4C920, 0xE4E920, 0xE4EA20,
|
||||
0xE520C7, 0xE5C720, 0xE5C920, 0xE5E620, 0xE620C7, 0xE720C7, 0xE7C720, 0xE8C7E4, 0xE8E620, 0xE920C7, 0xEA20C7, 0xEA20E5, 0xEA20E8, 0xEAC920, 0xEAD120, 0xEAE620,
|
||||
}
|
||||
|
||||
func newRecognizer_8859_6(language string, ngram *[64]uint32) *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: "ISO-8859-6",
|
||||
language: language,
|
||||
charMap: &charMap_8859_6,
|
||||
ngram: ngram,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_8859_6_ar() *recognizerSingleByte {
|
||||
return newRecognizer_8859_6("ar", &ngrams_8859_6_ar)
|
||||
}
|
||||
|
||||
var charMap_8859_7 = [256]byte{
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x00,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0xA1, 0xA2, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0xDC, 0x20,
|
||||
0xDD, 0xDE, 0xDF, 0x20, 0xFC, 0x20, 0xFD, 0xFE,
|
||||
0xC0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xF0, 0xF1, 0x20, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xDC, 0xDD, 0xDE, 0xDF,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0x20,
|
||||
}
|
||||
|
||||
var ngrams_8859_7_el = [64]uint32{
|
||||
0x20E1ED, 0x20E1F0, 0x20E3E9, 0x20E4E9, 0x20E5F0, 0x20E720, 0x20EAE1, 0x20ECE5, 0x20EDE1, 0x20EF20, 0x20F0E1, 0x20F0EF, 0x20F0F1, 0x20F3F4, 0x20F3F5, 0x20F4E7,
|
||||
0x20F4EF, 0xDFE120, 0xE120E1, 0xE120F4, 0xE1E920, 0xE1ED20, 0xE1F0FC, 0xE1F220, 0xE3E9E1, 0xE5E920, 0xE5F220, 0xE720F4, 0xE7ED20, 0xE7F220, 0xE920F4, 0xE9E120,
|
||||
0xE9EADE, 0xE9F220, 0xEAE1E9, 0xEAE1F4, 0xECE520, 0xED20E1, 0xED20E5, 0xED20F0, 0xEDE120, 0xEFF220, 0xEFF520, 0xF0EFF5, 0xF0F1EF, 0xF0FC20, 0xF220E1, 0xF220E5,
|
||||
0xF220EA, 0xF220F0, 0xF220F4, 0xF3E520, 0xF3E720, 0xF3F4EF, 0xF4E120, 0xF4E1E9, 0xF4E7ED, 0xF4E7F2, 0xF4E9EA, 0xF4EF20, 0xF4EFF5, 0xF4F9ED, 0xF9ED20, 0xFEED20,
|
||||
}
|
||||
|
||||
func newRecognizer_8859_7(language string, ngram *[64]uint32) *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: "ISO-8859-7",
|
||||
hasC1ByteCharset: "windows-1253",
|
||||
language: language,
|
||||
charMap: &charMap_8859_7,
|
||||
ngram: ngram,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_8859_7_el() *recognizerSingleByte {
|
||||
return newRecognizer_8859_7("el", &ngrams_8859_7_el)
|
||||
}
|
||||
|
||||
var charMap_8859_8 = [256]byte{
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x00,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0xB5, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
|
||||
0xF8, 0xF9, 0xFA, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
}
|
||||
|
||||
var ngrams_8859_8_I_he = [64]uint32{
|
||||
0x20E0E5, 0x20E0E7, 0x20E0E9, 0x20E0FA, 0x20E1E9, 0x20E1EE, 0x20E4E0, 0x20E4E5, 0x20E4E9, 0x20E4EE, 0x20E4F2, 0x20E4F9, 0x20E4FA, 0x20ECE0, 0x20ECE4, 0x20EEE0,
|
||||
0x20F2EC, 0x20F9EC, 0xE0FA20, 0xE420E0, 0xE420E1, 0xE420E4, 0xE420EC, 0xE420EE, 0xE420F9, 0xE4E5E0, 0xE5E020, 0xE5ED20, 0xE5EF20, 0xE5F820, 0xE5FA20, 0xE920E4,
|
||||
0xE9E420, 0xE9E5FA, 0xE9E9ED, 0xE9ED20, 0xE9EF20, 0xE9F820, 0xE9FA20, 0xEC20E0, 0xEC20E4, 0xECE020, 0xECE420, 0xED20E0, 0xED20E1, 0xED20E4, 0xED20EC, 0xED20EE,
|
||||
0xED20F9, 0xEEE420, 0xEF20E4, 0xF0E420, 0xF0E920, 0xF0E9ED, 0xF2EC20, 0xF820E4, 0xF8E9ED, 0xF9EC20, 0xFA20E0, 0xFA20E1, 0xFA20E4, 0xFA20EC, 0xFA20EE, 0xFA20F9,
|
||||
}
|
||||
|
||||
var ngrams_8859_8_he = [64]uint32{
|
||||
0x20E0E5, 0x20E0EC, 0x20E4E9, 0x20E4EC, 0x20E4EE, 0x20E4F0, 0x20E9F0, 0x20ECF2, 0x20ECF9, 0x20EDE5, 0x20EDE9, 0x20EFE5, 0x20EFE9, 0x20F8E5, 0x20F8E9, 0x20FAE0,
|
||||
0x20FAE5, 0x20FAE9, 0xE020E4, 0xE020EC, 0xE020ED, 0xE020FA, 0xE0E420, 0xE0E5E4, 0xE0EC20, 0xE0EE20, 0xE120E4, 0xE120ED, 0xE120FA, 0xE420E4, 0xE420E9, 0xE420EC,
|
||||
0xE420ED, 0xE420EF, 0xE420F8, 0xE420FA, 0xE4EC20, 0xE5E020, 0xE5E420, 0xE7E020, 0xE9E020, 0xE9E120, 0xE9E420, 0xEC20E4, 0xEC20ED, 0xEC20FA, 0xECF220, 0xECF920,
|
||||
0xEDE9E9, 0xEDE9F0, 0xEDE9F8, 0xEE20E4, 0xEE20ED, 0xEE20FA, 0xEEE120, 0xEEE420, 0xF2E420, 0xF920E4, 0xF920ED, 0xF920FA, 0xF9E420, 0xFAE020, 0xFAE420, 0xFAE5E9,
|
||||
}
|
||||
|
||||
func newRecognizer_8859_8(language string, ngram *[64]uint32) *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: "ISO-8859-8",
|
||||
hasC1ByteCharset: "windows-1255",
|
||||
language: language,
|
||||
charMap: &charMap_8859_8,
|
||||
ngram: ngram,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_8859_8_I_he() *recognizerSingleByte {
|
||||
r := newRecognizer_8859_8("he", &ngrams_8859_8_I_he)
|
||||
r.charset = "ISO-8859-8-I"
|
||||
return r
|
||||
}
|
||||
|
||||
func newRecognizer_8859_8_he() *recognizerSingleByte {
|
||||
return newRecognizer_8859_8("he", &ngrams_8859_8_he)
|
||||
}
|
||||
|
||||
var charMap_8859_9 = [256]byte{
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x00,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0xAA, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0xB5, 0x20, 0x20,
|
||||
0x20, 0x20, 0xBA, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0x20,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0x69, 0xFE, 0xDF,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0x20,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF,
|
||||
}
|
||||
|
||||
var ngrams_8859_9_tr = [64]uint32{
|
||||
0x206261, 0x206269, 0x206275, 0x206461, 0x206465, 0x206765, 0x206861, 0x20696C, 0x206B61, 0x206B6F, 0x206D61, 0x206F6C, 0x207361, 0x207461, 0x207665, 0x207961,
|
||||
0x612062, 0x616B20, 0x616C61, 0x616D61, 0x616E20, 0x616EFD, 0x617220, 0x617261, 0x6172FD, 0x6173FD, 0x617961, 0x626972, 0x646120, 0x646520, 0x646920, 0x652062,
|
||||
0x65206B, 0x656469, 0x656E20, 0x657220, 0x657269, 0x657369, 0x696C65, 0x696E20, 0x696E69, 0x697220, 0x6C616E, 0x6C6172, 0x6C6520, 0x6C6572, 0x6E2061, 0x6E2062,
|
||||
0x6E206B, 0x6E6461, 0x6E6465, 0x6E6520, 0x6E6920, 0x6E696E, 0x6EFD20, 0x72696E, 0x72FD6E, 0x766520, 0x796120, 0x796F72, 0xFD6E20, 0xFD6E64, 0xFD6EFD, 0xFDF0FD,
|
||||
}
|
||||
|
||||
func newRecognizer_8859_9(language string, ngram *[64]uint32) *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: "ISO-8859-9",
|
||||
hasC1ByteCharset: "windows-1254",
|
||||
language: language,
|
||||
charMap: &charMap_8859_9,
|
||||
ngram: ngram,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_8859_9_tr() *recognizerSingleByte {
|
||||
return newRecognizer_8859_9("tr", &ngrams_8859_9_tr)
|
||||
}
|
||||
|
||||
var charMap_windows_1256 = [256]byte{
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x00,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x81, 0x20, 0x83, 0x20, 0x20, 0x20, 0x20,
|
||||
0x88, 0x20, 0x8A, 0x20, 0x9C, 0x8D, 0x8E, 0x8F,
|
||||
0x90, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x98, 0x20, 0x9A, 0x20, 0x9C, 0x20, 0x20, 0x9F,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0xAA, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0xB5, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7,
|
||||
0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF,
|
||||
0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0x20,
|
||||
0xD8, 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0x20, 0x20, 0x20, 0x20, 0xF4, 0x20, 0x20, 0x20,
|
||||
0x20, 0xF9, 0x20, 0xFB, 0xFC, 0x20, 0x20, 0xFF,
|
||||
}
|
||||
|
||||
var ngrams_windows_1256 = [64]uint32{
|
||||
0x20C7E1, 0x20C7E4, 0x20C8C7, 0x20DAE1, 0x20DDED, 0x20E1E1, 0x20E3E4, 0x20E6C7, 0xC720C7, 0xC7C120, 0xC7CA20, 0xC7D120, 0xC7E120, 0xC7E1C3, 0xC7E1C7, 0xC7E1C8,
|
||||
0xC7E1CA, 0xC7E1CC, 0xC7E1CD, 0xC7E1CF, 0xC7E1D3, 0xC7E1DA, 0xC7E1DE, 0xC7E1E3, 0xC7E1E6, 0xC7E1ED, 0xC7E320, 0xC7E420, 0xC7E4CA, 0xC820C7, 0xC920C7, 0xC920DD,
|
||||
0xC920E1, 0xC920E3, 0xC920E6, 0xCA20C7, 0xCF20C7, 0xCFC920, 0xD120C7, 0xD1C920, 0xD320C7, 0xDA20C7, 0xDAE1EC, 0xDDED20, 0xE120C7, 0xE1C920, 0xE1EC20, 0xE1ED20,
|
||||
0xE320C7, 0xE3C720, 0xE3C920, 0xE3E420, 0xE420C7, 0xE520C7, 0xE5C720, 0xE6C7E1, 0xE6E420, 0xEC20C7, 0xED20C7, 0xED20E3, 0xED20E6, 0xEDC920, 0xEDD120, 0xEDE420,
|
||||
}
|
||||
|
||||
func newRecognizer_windows_1256() *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: "windows-1256",
|
||||
language: "ar",
|
||||
charMap: &charMap_windows_1256,
|
||||
ngram: &ngrams_windows_1256,
|
||||
}
|
||||
}
|
||||
|
||||
var charMap_windows_1251 = [256]byte{
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x00,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x90, 0x83, 0x20, 0x83, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x9A, 0x20, 0x9C, 0x9D, 0x9E, 0x9F,
|
||||
0x90, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x9A, 0x20, 0x9C, 0x9D, 0x9E, 0x9F,
|
||||
0x20, 0xA2, 0xA2, 0xBC, 0x20, 0xB4, 0x20, 0x20,
|
||||
0xB8, 0x20, 0xBA, 0x20, 0x20, 0x20, 0x20, 0xBF,
|
||||
0x20, 0x20, 0xB3, 0xB3, 0xB4, 0xB5, 0x20, 0x20,
|
||||
0xB8, 0x20, 0xBA, 0x20, 0xBC, 0xBE, 0xBE, 0xBF,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF,
|
||||
0xE0, 0xE1, 0xE2, 0xE3, 0xE4, 0xE5, 0xE6, 0xE7,
|
||||
0xE8, 0xE9, 0xEA, 0xEB, 0xEC, 0xED, 0xEE, 0xEF,
|
||||
0xF0, 0xF1, 0xF2, 0xF3, 0xF4, 0xF5, 0xF6, 0xF7,
|
||||
0xF8, 0xF9, 0xFA, 0xFB, 0xFC, 0xFD, 0xFE, 0xFF,
|
||||
}
|
||||
|
||||
var ngrams_windows_1251 = [64]uint32{
|
||||
0x20E220, 0x20E2EE, 0x20E4EE, 0x20E7E0, 0x20E820, 0x20EAE0, 0x20EAEE, 0x20EDE0, 0x20EDE5, 0x20EEE1, 0x20EFEE, 0x20EFF0, 0x20F0E0, 0x20F1EE, 0x20F1F2, 0x20F2EE,
|
||||
0x20F7F2, 0x20FDF2, 0xE0EDE8, 0xE0F2FC, 0xE3EE20, 0xE5EBFC, 0xE5EDE8, 0xE5F1F2, 0xE5F220, 0xE820EF, 0xE8E520, 0xE8E820, 0xE8FF20, 0xEBE5ED, 0xEBE820, 0xEBFCED,
|
||||
0xEDE020, 0xEDE520, 0xEDE8E5, 0xEDE8FF, 0xEDEE20, 0xEDEEE2, 0xEE20E2, 0xEE20EF, 0xEE20F1, 0xEEE220, 0xEEE2E0, 0xEEE3EE, 0xEEE920, 0xEEEBFC, 0xEEEC20, 0xEEF1F2,
|
||||
0xEFEEEB, 0xEFF0E5, 0xEFF0E8, 0xEFF0EE, 0xF0E0E2, 0xF0E5E4, 0xF1F2E0, 0xF1F2E2, 0xF1F2E8, 0xF1FF20, 0xF2E5EB, 0xF2EE20, 0xF2EEF0, 0xF2FC20, 0xF7F2EE, 0xFBF520,
|
||||
}
|
||||
|
||||
func newRecognizer_windows_1251() *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: "windows-1251",
|
||||
language: "ar",
|
||||
charMap: &charMap_windows_1251,
|
||||
ngram: &ngrams_windows_1251,
|
||||
}
|
||||
}
|
||||
|
||||
var charMap_KOI8_R = [256]byte{
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x00,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x61, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67,
|
||||
0x68, 0x69, 0x6A, 0x6B, 0x6C, 0x6D, 0x6E, 0x6F,
|
||||
0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77,
|
||||
0x78, 0x79, 0x7A, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0xA3, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0xA3, 0x20, 0x20, 0x20, 0x20,
|
||||
0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20, 0x20,
|
||||
0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7,
|
||||
0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF,
|
||||
0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7,
|
||||
0xD8, 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF,
|
||||
0xC0, 0xC1, 0xC2, 0xC3, 0xC4, 0xC5, 0xC6, 0xC7,
|
||||
0xC8, 0xC9, 0xCA, 0xCB, 0xCC, 0xCD, 0xCE, 0xCF,
|
||||
0xD0, 0xD1, 0xD2, 0xD3, 0xD4, 0xD5, 0xD6, 0xD7,
|
||||
0xD8, 0xD9, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF,
|
||||
}
|
||||
|
||||
var ngrams_KOI8_R = [64]uint32{
|
||||
0x20C4CF, 0x20C920, 0x20CBC1, 0x20CBCF, 0x20CEC1, 0x20CEC5, 0x20CFC2, 0x20D0CF, 0x20D0D2, 0x20D2C1, 0x20D3CF, 0x20D3D4, 0x20D4CF, 0x20D720, 0x20D7CF, 0x20DAC1,
|
||||
0x20DCD4, 0x20DED4, 0xC1CEC9, 0xC1D4D8, 0xC5CCD8, 0xC5CEC9, 0xC5D3D4, 0xC5D420, 0xC7CF20, 0xC920D0, 0xC9C520, 0xC9C920, 0xC9D120, 0xCCC5CE, 0xCCC920, 0xCCD8CE,
|
||||
0xCEC120, 0xCEC520, 0xCEC9C5, 0xCEC9D1, 0xCECF20, 0xCECFD7, 0xCF20D0, 0xCF20D3, 0xCF20D7, 0xCFC7CF, 0xCFCA20, 0xCFCCD8, 0xCFCD20, 0xCFD3D4, 0xCFD720, 0xCFD7C1,
|
||||
0xD0CFCC, 0xD0D2C5, 0xD0D2C9, 0xD0D2CF, 0xD2C1D7, 0xD2C5C4, 0xD3D120, 0xD3D4C1, 0xD3D4C9, 0xD3D4D7, 0xD4C5CC, 0xD4CF20, 0xD4CFD2, 0xD4D820, 0xD9C820, 0xDED4CF,
|
||||
}
|
||||
|
||||
func newRecognizer_KOI8_R() *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: "KOI8-R",
|
||||
language: "ru",
|
||||
charMap: &charMap_KOI8_R,
|
||||
ngram: &ngrams_KOI8_R,
|
||||
}
|
||||
}
|
||||
|
||||
var charMap_IBM424_he = [256]byte{
|
||||
/* -0 -1 -2 -3 -4 -5 -6 -7 -8 -9 -A -B -C -D -E -F */
|
||||
/* 0- */ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 1- */ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 2- */ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 3- */ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 4- */ 0x40, 0x41, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 5- */ 0x40, 0x51, 0x52, 0x53, 0x54, 0x55, 0x56, 0x57, 0x58, 0x59, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 6- */ 0x40, 0x40, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 7- */ 0x40, 0x71, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x00, 0x40, 0x40,
|
||||
/* 8- */ 0x40, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 9- */ 0x40, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* A- */ 0xA0, 0x40, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* B- */ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* C- */ 0x40, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* D- */ 0x40, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* E- */ 0x40, 0x40, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* F- */ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
}
|
||||
|
||||
var ngrams_IBM424_he_rtl = [64]uint32{
|
||||
0x404146, 0x404148, 0x404151, 0x404171, 0x404251, 0x404256, 0x404541, 0x404546, 0x404551, 0x404556, 0x404562, 0x404569, 0x404571, 0x405441, 0x405445, 0x405641,
|
||||
0x406254, 0x406954, 0x417140, 0x454041, 0x454042, 0x454045, 0x454054, 0x454056, 0x454069, 0x454641, 0x464140, 0x465540, 0x465740, 0x466840, 0x467140, 0x514045,
|
||||
0x514540, 0x514671, 0x515155, 0x515540, 0x515740, 0x516840, 0x517140, 0x544041, 0x544045, 0x544140, 0x544540, 0x554041, 0x554042, 0x554045, 0x554054, 0x554056,
|
||||
0x554069, 0x564540, 0x574045, 0x584540, 0x585140, 0x585155, 0x625440, 0x684045, 0x685155, 0x695440, 0x714041, 0x714042, 0x714045, 0x714054, 0x714056, 0x714069,
|
||||
}
|
||||
|
||||
var ngrams_IBM424_he_ltr = [64]uint32{
|
||||
0x404146, 0x404154, 0x404551, 0x404554, 0x404556, 0x404558, 0x405158, 0x405462, 0x405469, 0x405546, 0x405551, 0x405746, 0x405751, 0x406846, 0x406851, 0x407141,
|
||||
0x407146, 0x407151, 0x414045, 0x414054, 0x414055, 0x414071, 0x414540, 0x414645, 0x415440, 0x415640, 0x424045, 0x424055, 0x424071, 0x454045, 0x454051, 0x454054,
|
||||
0x454055, 0x454057, 0x454068, 0x454071, 0x455440, 0x464140, 0x464540, 0x484140, 0x514140, 0x514240, 0x514540, 0x544045, 0x544055, 0x544071, 0x546240, 0x546940,
|
||||
0x555151, 0x555158, 0x555168, 0x564045, 0x564055, 0x564071, 0x564240, 0x564540, 0x624540, 0x694045, 0x694055, 0x694071, 0x694540, 0x714140, 0x714540, 0x714651,
|
||||
}
|
||||
|
||||
func newRecognizer_IBM424_he(charset string, ngram *[64]uint32) *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: charset,
|
||||
language: "he",
|
||||
charMap: &charMap_IBM424_he,
|
||||
ngram: ngram,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_IBM424_he_rtl() *recognizerSingleByte {
|
||||
return newRecognizer_IBM424_he("IBM424_rtl", &ngrams_IBM424_he_rtl)
|
||||
}
|
||||
|
||||
func newRecognizer_IBM424_he_ltr() *recognizerSingleByte {
|
||||
return newRecognizer_IBM424_he("IBM424_ltr", &ngrams_IBM424_he_ltr)
|
||||
}
|
||||
|
||||
var charMap_IBM420_ar = [256]byte{
|
||||
/* -0 -1 -2 -3 -4 -5 -6 -7 -8 -9 -A -B -C -D -E -F */
|
||||
/* 0- */ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 1- */ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 2- */ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 3- */ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 4- */ 0x40, 0x40, 0x42, 0x43, 0x44, 0x45, 0x46, 0x47, 0x48, 0x49, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 5- */ 0x40, 0x51, 0x52, 0x40, 0x40, 0x55, 0x56, 0x57, 0x58, 0x59, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 6- */ 0x40, 0x40, 0x62, 0x63, 0x64, 0x65, 0x66, 0x67, 0x68, 0x69, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 7- */ 0x70, 0x71, 0x72, 0x73, 0x74, 0x75, 0x76, 0x77, 0x78, 0x79, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40,
|
||||
/* 8- */ 0x80, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x8A, 0x8B, 0x8C, 0x8D, 0x8E, 0x8F,
|
||||
/* 9- */ 0x90, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0x9A, 0x9B, 0x9C, 0x9D, 0x9E, 0x9F,
|
||||
/* A- */ 0xA0, 0x40, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xAA, 0xAB, 0xAC, 0xAD, 0xAE, 0xAF,
|
||||
/* B- */ 0xB0, 0xB1, 0xB2, 0xB3, 0xB4, 0xB5, 0x40, 0x40, 0xB8, 0xB9, 0xBA, 0xBB, 0xBC, 0xBD, 0xBE, 0xBF,
|
||||
/* C- */ 0x40, 0x81, 0x82, 0x83, 0x84, 0x85, 0x86, 0x87, 0x88, 0x89, 0x40, 0xCB, 0x40, 0xCD, 0x40, 0xCF,
|
||||
/* D- */ 0x40, 0x91, 0x92, 0x93, 0x94, 0x95, 0x96, 0x97, 0x98, 0x99, 0xDA, 0xDB, 0xDC, 0xDD, 0xDE, 0xDF,
|
||||
/* E- */ 0x40, 0x40, 0xA2, 0xA3, 0xA4, 0xA5, 0xA6, 0xA7, 0xA8, 0xA9, 0xEA, 0xEB, 0x40, 0xED, 0xEE, 0xEF,
|
||||
/* F- */ 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0x40, 0xFB, 0xFC, 0xFD, 0xFE, 0x40,
|
||||
}
|
||||
|
||||
var ngrams_IBM420_ar_rtl = [64]uint32{
|
||||
0x4056B1, 0x4056BD, 0x405856, 0x409AB1, 0x40ABDC, 0x40B1B1, 0x40BBBD, 0x40CF56, 0x564056, 0x564640, 0x566340, 0x567540, 0x56B140, 0x56B149, 0x56B156, 0x56B158,
|
||||
0x56B163, 0x56B167, 0x56B169, 0x56B173, 0x56B178, 0x56B19A, 0x56B1AD, 0x56B1BB, 0x56B1CF, 0x56B1DC, 0x56BB40, 0x56BD40, 0x56BD63, 0x584056, 0x624056, 0x6240AB,
|
||||
0x6240B1, 0x6240BB, 0x6240CF, 0x634056, 0x734056, 0x736240, 0x754056, 0x756240, 0x784056, 0x9A4056, 0x9AB1DA, 0xABDC40, 0xB14056, 0xB16240, 0xB1DA40, 0xB1DC40,
|
||||
0xBB4056, 0xBB5640, 0xBB6240, 0xBBBD40, 0xBD4056, 0xBF4056, 0xBF5640, 0xCF56B1, 0xCFBD40, 0xDA4056, 0xDC4056, 0xDC40BB, 0xDC40CF, 0xDC6240, 0xDC7540, 0xDCBD40,
|
||||
}
|
||||
|
||||
var ngrams_IBM420_ar_ltr = [64]uint32{
|
||||
0x404656, 0x4056BB, 0x4056BF, 0x406273, 0x406275, 0x4062B1, 0x4062BB, 0x4062DC, 0x406356, 0x407556, 0x4075DC, 0x40B156, 0x40BB56, 0x40BD56, 0x40BDBB, 0x40BDCF,
|
||||
0x40BDDC, 0x40DAB1, 0x40DCAB, 0x40DCB1, 0x49B156, 0x564056, 0x564058, 0x564062, 0x564063, 0x564073, 0x564075, 0x564078, 0x56409A, 0x5640B1, 0x5640BB, 0x5640BD,
|
||||
0x5640BF, 0x5640DA, 0x5640DC, 0x565840, 0x56B156, 0x56CF40, 0x58B156, 0x63B156, 0x63BD56, 0x67B156, 0x69B156, 0x73B156, 0x78B156, 0x9AB156, 0xAB4062, 0xADB156,
|
||||
0xB14062, 0xB15640, 0xB156CF, 0xB19A40, 0xB1B140, 0xBB4062, 0xBB40DC, 0xBBB156, 0xBD5640, 0xBDBB40, 0xCF4062, 0xCF40DC, 0xCFB156, 0xDAB19A, 0xDCAB40, 0xDCB156,
|
||||
}
|
||||
|
||||
func newRecognizer_IBM420_ar(charset string, ngram *[64]uint32) *recognizerSingleByte {
|
||||
return &recognizerSingleByte{
|
||||
charset: charset,
|
||||
language: "ar",
|
||||
charMap: &charMap_IBM420_ar,
|
||||
ngram: ngram,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_IBM420_ar_rtl() *recognizerSingleByte {
|
||||
return newRecognizer_IBM420_ar("IBM420_rtl", &ngrams_IBM420_ar_rtl)
|
||||
}
|
||||
|
||||
func newRecognizer_IBM420_ar_ltr() *recognizerSingleByte {
|
||||
return newRecognizer_IBM420_ar("IBM420_ltr", &ngrams_IBM420_ar_ltr)
|
||||
}
|
||||
|
|
@ -1,103 +0,0 @@
|
|||
package chardet
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
)
|
||||
|
||||
var (
|
||||
utf16beBom = []byte{0xFE, 0xFF}
|
||||
utf16leBom = []byte{0xFF, 0xFE}
|
||||
utf32beBom = []byte{0x00, 0x00, 0xFE, 0xFF}
|
||||
utf32leBom = []byte{0xFF, 0xFE, 0x00, 0x00}
|
||||
)
|
||||
|
||||
type recognizerUtf16be struct {
|
||||
}
|
||||
|
||||
func newRecognizer_utf16be() *recognizerUtf16be {
|
||||
return &recognizerUtf16be{}
|
||||
}
|
||||
|
||||
func (*recognizerUtf16be) Match(input *recognizerInput) (output recognizerOutput) {
|
||||
output = recognizerOutput{
|
||||
Charset: "UTF-16BE",
|
||||
}
|
||||
if bytes.HasPrefix(input.raw, utf16beBom) {
|
||||
output.Confidence = 100
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
type recognizerUtf16le struct {
|
||||
}
|
||||
|
||||
func newRecognizer_utf16le() *recognizerUtf16le {
|
||||
return &recognizerUtf16le{}
|
||||
}
|
||||
|
||||
func (*recognizerUtf16le) Match(input *recognizerInput) (output recognizerOutput) {
|
||||
output = recognizerOutput{
|
||||
Charset: "UTF-16LE",
|
||||
}
|
||||
if bytes.HasPrefix(input.raw, utf16leBom) && !bytes.HasPrefix(input.raw, utf32leBom) {
|
||||
output.Confidence = 100
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
type recognizerUtf32 struct {
|
||||
name string
|
||||
bom []byte
|
||||
decodeChar func(input []byte) uint32
|
||||
}
|
||||
|
||||
func decodeUtf32be(input []byte) uint32 {
|
||||
return uint32(input[0])<<24 | uint32(input[1])<<16 | uint32(input[2])<<8 | uint32(input[3])
|
||||
}
|
||||
|
||||
func decodeUtf32le(input []byte) uint32 {
|
||||
return uint32(input[3])<<24 | uint32(input[2])<<16 | uint32(input[1])<<8 | uint32(input[0])
|
||||
}
|
||||
|
||||
func newRecognizer_utf32be() *recognizerUtf32 {
|
||||
return &recognizerUtf32{
|
||||
"UTF-32BE",
|
||||
utf32beBom,
|
||||
decodeUtf32be,
|
||||
}
|
||||
}
|
||||
|
||||
func newRecognizer_utf32le() *recognizerUtf32 {
|
||||
return &recognizerUtf32{
|
||||
"UTF-32LE",
|
||||
utf32leBom,
|
||||
decodeUtf32le,
|
||||
}
|
||||
}
|
||||
|
||||
func (r *recognizerUtf32) Match(input *recognizerInput) (output recognizerOutput) {
|
||||
output = recognizerOutput{
|
||||
Charset: r.name,
|
||||
}
|
||||
hasBom := bytes.HasPrefix(input.raw, r.bom)
|
||||
var numValid, numInvalid uint32
|
||||
for b := input.raw; len(b) >= 4; b = b[4:] {
|
||||
if c := r.decodeChar(b); c >= 0x10FFFF || (c >= 0xD800 && c <= 0xDFFF) {
|
||||
numInvalid++
|
||||
} else {
|
||||
numValid++
|
||||
}
|
||||
}
|
||||
if hasBom && numInvalid == 0 {
|
||||
output.Confidence = 100
|
||||
} else if hasBom && numValid > numInvalid*10 {
|
||||
output.Confidence = 80
|
||||
} else if numValid > 3 && numInvalid == 0 {
|
||||
output.Confidence = 100
|
||||
} else if numValid > 0 && numInvalid == 0 {
|
||||
output.Confidence = 80
|
||||
} else if numValid > numInvalid*10 {
|
||||
output.Confidence = 25
|
||||
}
|
||||
return
|
||||
}
|
||||
|
|
@ -1,71 +0,0 @@
|
|||
package chardet
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
)
|
||||
|
||||
var utf8Bom = []byte{0xEF, 0xBB, 0xBF}
|
||||
|
||||
type recognizerUtf8 struct {
|
||||
}
|
||||
|
||||
func newRecognizer_utf8() *recognizerUtf8 {
|
||||
return &recognizerUtf8{}
|
||||
}
|
||||
|
||||
func (*recognizerUtf8) Match(input *recognizerInput) (output recognizerOutput) {
|
||||
output = recognizerOutput{
|
||||
Charset: "UTF-8",
|
||||
}
|
||||
hasBom := bytes.HasPrefix(input.raw, utf8Bom)
|
||||
inputLen := len(input.raw)
|
||||
var numValid, numInvalid uint32
|
||||
var trailBytes uint8
|
||||
for i := 0; i < inputLen; i++ {
|
||||
c := input.raw[i]
|
||||
if c&0x80 == 0 {
|
||||
continue
|
||||
}
|
||||
if c&0xE0 == 0xC0 {
|
||||
trailBytes = 1
|
||||
} else if c&0xF0 == 0xE0 {
|
||||
trailBytes = 2
|
||||
} else if c&0xF8 == 0xF0 {
|
||||
trailBytes = 3
|
||||
} else {
|
||||
numInvalid++
|
||||
if numInvalid > 5 {
|
||||
break
|
||||
}
|
||||
trailBytes = 0
|
||||
}
|
||||
|
||||
for i++; i < inputLen; i++ {
|
||||
c = input.raw[i]
|
||||
if c&0xC0 != 0x80 {
|
||||
numInvalid++
|
||||
break
|
||||
}
|
||||
if trailBytes--; trailBytes == 0 {
|
||||
numValid++
|
||||
break
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if hasBom && numInvalid == 0 {
|
||||
output.Confidence = 100
|
||||
} else if hasBom && numValid > numInvalid*10 {
|
||||
output.Confidence = 80
|
||||
} else if numValid > 3 && numInvalid == 0 {
|
||||
output.Confidence = 100
|
||||
} else if numValid > 0 && numInvalid == 0 {
|
||||
output.Confidence = 80
|
||||
} else if numValid == 0 && numInvalid == 0 {
|
||||
// Plain ASCII
|
||||
output.Confidence = 10
|
||||
} else if numValid > numInvalid*10 {
|
||||
output.Confidence = 25
|
||||
}
|
||||
return
|
||||
}
|
||||
|
|
@ -1,10 +0,0 @@
|
|||
*.cgo?.*
|
||||
*.o
|
||||
*.so
|
||||
*.sublime-*
|
||||
.DS_Store
|
||||
.idea/
|
||||
_cgo_*
|
||||
_obj
|
||||
_test
|
||||
coverage.txt
|
||||
|
|
@ -1,20 +0,0 @@
|
|||
linters:
|
||||
enable:
|
||||
- goconst
|
||||
- gofmt
|
||||
- gosec
|
||||
- maligned
|
||||
- prealloc
|
||||
- staticcheck
|
||||
disable:
|
||||
- deadcode
|
||||
- structcheck
|
||||
- varcheck
|
||||
|
||||
linters-settings:
|
||||
gofmt:
|
||||
simplify: true
|
||||
govet:
|
||||
check-shadowing: true
|
||||
maligned:
|
||||
suggest-new: true
|
||||
|
|
@ -1,35 +0,0 @@
|
|||
cache:
|
||||
go: true
|
||||
directories:
|
||||
- $HOME/.cache
|
||||
- $HOME/bin
|
||||
- $HOME/gopath/pkg/mod
|
||||
language: go
|
||||
go:
|
||||
- 1.11
|
||||
- 1.12
|
||||
- master
|
||||
install: true
|
||||
script: GO111MODULE=on go test -race
|
||||
|
||||
matrix:
|
||||
include:
|
||||
- go: 1.7
|
||||
install: go get -t
|
||||
- go: 1.8
|
||||
install: go get -t
|
||||
- go: 1.9
|
||||
install: go get -t
|
||||
- go: 1.10.x
|
||||
install: go get -t
|
||||
- go: 1.x
|
||||
env: task=coverage
|
||||
script: GO111MODULE=on go test -race -covermode=atomic -coverprofile=coverage.txt
|
||||
after_success: bash <(curl -s https://codecov.io/bash)
|
||||
- go: 1.x
|
||||
env: task=bench
|
||||
script: GO111MODULE=on ./script/bench
|
||||
- go: 1.x
|
||||
install: curl -sfL https://install.goreleaser.com/github.com/golangci/golangci-lint.sh | bash -s -- -b $HOME/bin v1.16.0
|
||||
env: task=clean
|
||||
script: GO111MODULE=on ./script/clean
|
||||
|
|
@ -1,21 +0,0 @@
|
|||
The MIT License
|
||||
|
||||
Copyright (c) 2010 Sergey Shepelev <temotor@gmail.com>
|
||||
|
||||
Permission is hereby granted, free of charge, to any person obtaining a copy
|
||||
of this software and associated documentation files (the "Software"), to deal
|
||||
in the Software without restriction, including without limitation the rights
|
||||
to use, copy, modify, merge, publish, distribute, sublicense, and/or sell
|
||||
copies of the Software, and to permit persons to whom the Software is
|
||||
furnished to do so, subject to the following conditions:
|
||||
|
||||
The above copyright notice and this permission notice shall be included in
|
||||
all copies or substantial portions of the Software.
|
||||
|
||||
THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
|
||||
IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
|
||||
FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
|
||||
AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
|
||||
LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
|
||||
OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN
|
||||
THE SOFTWARE.
|
||||
|
|
@ -1,115 +0,0 @@
|
|||
What
|
||||
====
|
||||
|
||||
This is a robots.txt exclusion protocol implementation for Go language (golang).
|
||||
|
||||
|
||||
Build
|
||||
=====
|
||||
|
||||
To build and run tests run `script/test` in source directory.
|
||||
|
||||
|
||||
Contribute
|
||||
==========
|
||||
|
||||
Warm welcome.
|
||||
|
||||
* If desired, add your name in README.rst, section Who.
|
||||
* Run `script/test && script/clean && echo ok`
|
||||
* You can ignore linter warnings, but everything else must pass.
|
||||
* Send your change as pull request or just a regular patch to current maintainer (see section Who).
|
||||
|
||||
Thank you.
|
||||
|
||||
|
||||
Usage
|
||||
=====
|
||||
|
||||
As usual, no special installation is required, just
|
||||
|
||||
import "github.com/temoto/robotstxt"
|
||||
|
||||
run `go get` and you're ready.
|
||||
|
||||
1. Parse
|
||||
^^^^^^^^
|
||||
|
||||
First of all, you need to parse robots.txt data. You can do it with
|
||||
functions `FromBytes(body []byte) (*RobotsData, error)` or same for `string`::
|
||||
|
||||
robots, err := robotstxt.FromBytes([]byte("User-agent: *\nDisallow:"))
|
||||
robots, err := robotstxt.FromString("User-agent: *\nDisallow:")
|
||||
|
||||
As of 2012-10-03, `FromBytes` is the most efficient method, everything else
|
||||
is a wrapper for this core function.
|
||||
|
||||
There are few convenient constructors for various purposes:
|
||||
|
||||
* `FromResponse(*http.Response) (*RobotsData, error)` to init robots data
|
||||
from HTTP response. It *does not* call `response.Body.Close()`::
|
||||
|
||||
robots, err := robotstxt.FromResponse(resp)
|
||||
resp.Body.Close()
|
||||
if err != nil {
|
||||
log.Println("Error parsing robots.txt:", err.Error())
|
||||
}
|
||||
|
||||
* `FromStatusAndBytes(statusCode int, body []byte) (*RobotsData, error)` or
|
||||
`FromStatusAndString` if you prefer to read bytes (string) yourself.
|
||||
Passing status code applies following logic in line with Google's interpretation
|
||||
of robots.txt files:
|
||||
|
||||
* status 2xx -> parse body with `FromBytes` and apply rules listed there.
|
||||
* status 4xx -> allow all (even 401/403, as recommended by Google).
|
||||
* other (5xx) -> disallow all, consider this a temporary unavailability.
|
||||
|
||||
2. Query
|
||||
^^^^^^^^
|
||||
|
||||
Parsing robots.txt content builds a kind of logic database, which you can
|
||||
query with `(r *RobotsData) TestAgent(url, agent string) (bool)`.
|
||||
|
||||
Explicit passing of agent is useful if you want to query for different agents. For
|
||||
single agent users there is an efficient option: `RobotsData.FindGroup(userAgent string)`
|
||||
returns a structure with `.Test(path string)` method and `.CrawlDelay time.Duration`.
|
||||
|
||||
Simple query with explicit user agent. Each call will scan all rules.
|
||||
|
||||
::
|
||||
|
||||
allow := robots.TestAgent("/", "FooBot")
|
||||
|
||||
Or query several paths against same user agent for performance.
|
||||
|
||||
::
|
||||
|
||||
group := robots.FindGroup("BarBot")
|
||||
group.Test("/")
|
||||
group.Test("/download.mp3")
|
||||
group.Test("/news/article-2012-1")
|
||||
|
||||
|
||||
Who
|
||||
===
|
||||
|
||||
Honorable contributors (in undefined order):
|
||||
|
||||
* Ilya Grigorik (igrigorik)
|
||||
* Martin Angers (PuerkitoBio)
|
||||
* Micha Gorelick (mynameisfiber)
|
||||
|
||||
Initial commit and other: Sergey Shepelev temotor@gmail.com
|
||||
|
||||
|
||||
Flair
|
||||
=====
|
||||
|
||||
.. image:: https://travis-ci.org/temoto/robotstxt.svg?branch=master
|
||||
:target: https://travis-ci.org/temoto/robotstxt
|
||||
|
||||
.. image:: https://codecov.io/gh/temoto/robotstxt/branch/master/graph/badge.svg
|
||||
:target: https://codecov.io/gh/temoto/robotstxt
|
||||
|
||||
.. image:: https://goreportcard.com/badge/github.com/temoto/robotstxt
|
||||
:target: https://goreportcard.com/report/github.com/temoto/robotstxt
|
||||
|
|
@ -1,2 +0,0 @@
|
|||
codecov:
|
||||
token: 6bf9c7eb-69ff-4b74-8464-e2fb452d0f04
|
||||
|
|
@ -1,5 +0,0 @@
|
|||
module github.com/temoto/robotstxt
|
||||
|
||||
go 1.11
|
||||
|
||||
require github.com/stretchr/testify v1.3.0
|
||||
|
|
@ -1,7 +0,0 @@
|
|||
github.com/davecgh/go-spew v1.1.0 h1:ZDRjVQ15GmhC3fiQ8ni8+OwkZQO4DARzQgrnXU1Liz8=
|
||||
github.com/davecgh/go-spew v1.1.0/go.mod h1:J7Y8YcW2NihsgmVo/mv3lAwl/skON4iLHjSsI+c5H38=
|
||||
github.com/pmezard/go-difflib v1.0.0 h1:4DBwDE0NGyQoBHbLQYPwSUPoCMWR5BEzIk/f1lZbAQM=
|
||||
github.com/pmezard/go-difflib v1.0.0/go.mod h1:iKH77koFhYxTK1pcRnkKkqfTogsbg7gZNVY4sRDYZ/4=
|
||||
github.com/stretchr/objx v0.1.0/go.mod h1:HFkY916IF+rwdDfMAkV7OtwuqBVzrE8GR6GFx+wExME=
|
||||
github.com/stretchr/testify v1.3.0 h1:TivCn/peBQ7UY8ooIcPgZFpTNSz0Q2U6UrFlUfqbe0Q=
|
||||
github.com/stretchr/testify v1.3.0/go.mod h1:M5WIy9Dh21IEIfnGCwXGc5bZfKNJtfHm1UVUgZn+9EI=
|
||||
|
|
@ -1,266 +0,0 @@
|
|||
package robotstxt
|
||||
|
||||
// Comments explaining the logic are taken from either the google's spec:
|
||||
// https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
|
||||
//
|
||||
// or the Wikipedia's entry on robots.txt:
|
||||
// http://en.wikipedia.org/wiki/Robots.txt
|
||||
|
||||
import (
|
||||
"fmt"
|
||||
"io"
|
||||
"regexp"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
|
||||
type lineType uint
|
||||
|
||||
const (
|
||||
lIgnore lineType = iota
|
||||
lUnknown
|
||||
lUserAgent
|
||||
lAllow
|
||||
lDisallow
|
||||
lCrawlDelay
|
||||
lSitemap
|
||||
lHost
|
||||
)
|
||||
|
||||
type parser struct {
|
||||
tokens []string
|
||||
pos int
|
||||
}
|
||||
|
||||
type lineInfo struct {
|
||||
t lineType // Type of line key
|
||||
k string // String representation of the type of key
|
||||
vs string // String value of the key
|
||||
vf float64 // Float value of the key
|
||||
vr *regexp.Regexp // Regexp value of the key
|
||||
}
|
||||
|
||||
func newParser(tokens []string) *parser {
|
||||
return &parser{tokens: tokens}
|
||||
}
|
||||
|
||||
func parseGroupMap(groups map[string]*Group, agents []string, fun func(*Group)) {
|
||||
var g *Group
|
||||
for _, a := range agents {
|
||||
if g = groups[a]; g == nil {
|
||||
g = new(Group)
|
||||
groups[a] = g
|
||||
}
|
||||
fun(g)
|
||||
}
|
||||
}
|
||||
|
||||
func (p *parser) parseAll() (groups map[string]*Group, host string, sitemaps []string, errs []error) {
|
||||
groups = make(map[string]*Group, 16)
|
||||
agents := make([]string, 0, 4)
|
||||
isEmptyGroup := true
|
||||
|
||||
// Reset internal fields, tokens are assigned at creation time, never change
|
||||
p.pos = 0
|
||||
|
||||
for {
|
||||
if li, err := p.parseLine(); err != nil {
|
||||
if err == io.EOF {
|
||||
break
|
||||
}
|
||||
errs = append(errs, err)
|
||||
} else {
|
||||
switch li.t {
|
||||
case lUserAgent:
|
||||
// Two successive user-agent lines are part of the same group.
|
||||
if !isEmptyGroup {
|
||||
// End previous group
|
||||
agents = make([]string, 0, 4)
|
||||
}
|
||||
if len(agents) == 0 {
|
||||
isEmptyGroup = true
|
||||
}
|
||||
agents = append(agents, li.vs)
|
||||
|
||||
case lDisallow:
|
||||
// Error if no current group
|
||||
if len(agents) == 0 {
|
||||
errs = append(errs, fmt.Errorf("Disallow before User-agent at token #%d.", p.pos))
|
||||
} else {
|
||||
isEmptyGroup = false
|
||||
var r *rule
|
||||
if li.vr != nil {
|
||||
r = &rule{"", false, li.vr}
|
||||
} else {
|
||||
r = &rule{li.vs, false, nil}
|
||||
}
|
||||
parseGroupMap(groups, agents, func(g *Group) { g.rules = append(g.rules, r) })
|
||||
}
|
||||
|
||||
case lAllow:
|
||||
// Error if no current group
|
||||
if len(agents) == 0 {
|
||||
errs = append(errs, fmt.Errorf("Allow before User-agent at token #%d.", p.pos))
|
||||
} else {
|
||||
isEmptyGroup = false
|
||||
var r *rule
|
||||
if li.vr != nil {
|
||||
r = &rule{"", true, li.vr}
|
||||
} else {
|
||||
r = &rule{li.vs, true, nil}
|
||||
}
|
||||
parseGroupMap(groups, agents, func(g *Group) { g.rules = append(g.rules, r) })
|
||||
}
|
||||
|
||||
case lHost:
|
||||
host = li.vs
|
||||
|
||||
case lSitemap:
|
||||
sitemaps = append(sitemaps, li.vs)
|
||||
|
||||
case lCrawlDelay:
|
||||
if len(agents) == 0 {
|
||||
errs = append(errs, fmt.Errorf("Crawl-delay before User-agent at token #%d.", p.pos))
|
||||
} else {
|
||||
isEmptyGroup = false
|
||||
delay := time.Duration(li.vf * float64(time.Second))
|
||||
parseGroupMap(groups, agents, func(g *Group) { g.CrawlDelay = delay })
|
||||
}
|
||||
}
|
||||
}
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
func (p *parser) parseLine() (li *lineInfo, err error) {
|
||||
t1, ok1 := p.popToken()
|
||||
if !ok1 {
|
||||
// proper EOF
|
||||
return nil, io.EOF
|
||||
}
|
||||
|
||||
t2, ok2 := p.peekToken()
|
||||
if !ok2 {
|
||||
// EOF, no value associated with the token, so ignore token and return
|
||||
return nil, io.EOF
|
||||
}
|
||||
|
||||
// Helper closure for all string-based tokens, common behaviour:
|
||||
// - Consume t2 token
|
||||
// - If empty, return unknown line info
|
||||
// - Otherwise return the specified line info
|
||||
returnStringVal := func(t lineType) (*lineInfo, error) {
|
||||
p.popToken()
|
||||
if t2 != "" {
|
||||
return &lineInfo{t: t, k: t1, vs: t2}, nil
|
||||
}
|
||||
return &lineInfo{t: lIgnore}, nil
|
||||
}
|
||||
|
||||
// Helper closure for all path tokens (allow/disallow), common behaviour:
|
||||
// - Consume t2 token
|
||||
// - If empty, return unknown line info
|
||||
// - Otherwise, normalize the path (add leading "/" if missing, remove trailing "*")
|
||||
// - Detect if wildcards are present, if so, compile into a regexp
|
||||
// - Return the specified line info
|
||||
returnPathVal := func(t lineType) (*lineInfo, error) {
|
||||
p.popToken()
|
||||
if t2 != "" {
|
||||
if !strings.HasPrefix(t2, "*") && !strings.HasPrefix(t2, "/") {
|
||||
t2 = "/" + t2
|
||||
}
|
||||
if strings.HasSuffix(t2, "*") {
|
||||
t2 = strings.TrimRight(t2, "*")
|
||||
}
|
||||
// From google's spec:
|
||||
// Google, Bing, Yahoo, and Ask support a limited form of
|
||||
// "wildcards" for path values. These are:
|
||||
// * designates 0 or more instances of any valid character
|
||||
// $ designates the end of the URL
|
||||
if strings.ContainsAny(t2, "*$") {
|
||||
// Must compile a regexp, this is a pattern.
|
||||
// Escape string before compile.
|
||||
t2 = regexp.QuoteMeta(t2)
|
||||
t2 = strings.Replace(t2, `\*`, `.*`, -1)
|
||||
t2 = strings.Replace(t2, `\$`, `$`, -1)
|
||||
if r, e := regexp.Compile(t2); e != nil {
|
||||
return nil, e
|
||||
} else {
|
||||
return &lineInfo{t: t, k: t1, vr: r}, nil
|
||||
}
|
||||
} else {
|
||||
// Simple string path
|
||||
return &lineInfo{t: t, k: t1, vs: t2}, nil
|
||||
}
|
||||
}
|
||||
return &lineInfo{t: lIgnore}, nil
|
||||
}
|
||||
|
||||
switch strings.ToLower(t1) {
|
||||
case tokEOL:
|
||||
// Don't consume t2 and continue parsing
|
||||
return &lineInfo{t: lIgnore}, nil
|
||||
|
||||
case "user-agent", "useragent":
|
||||
// From google's spec:
|
||||
// Handling of <field> elements with simple errors / typos (eg "useragent"
|
||||
// instead of "user-agent") is undefined and may be interpreted as correct
|
||||
// directives by some user-agents.
|
||||
// The user-agent is non-case-sensitive.
|
||||
t2 = strings.ToLower(t2)
|
||||
return returnStringVal(lUserAgent)
|
||||
|
||||
case "disallow":
|
||||
// From google's spec:
|
||||
// When no path is specified, the directive is ignored (so an empty Disallow
|
||||
// CAN be an allow, since allow is the default. The actual result depends
|
||||
// on the other rules in the group).
|
||||
return returnPathVal(lDisallow)
|
||||
|
||||
case "allow":
|
||||
// From google's spec:
|
||||
// When no path is specified, the directive is ignored.
|
||||
return returnPathVal(lAllow)
|
||||
|
||||
case "host":
|
||||
// Host directive to specify main site mirror
|
||||
// Read more: https://help.yandex.com/webmaster/controlling-robot/robots-txt.xml#host
|
||||
return returnStringVal(lHost)
|
||||
|
||||
case "sitemap":
|
||||
// Non-group field, applies to the host as a whole, not to a specific user-agent
|
||||
return returnStringVal(lSitemap)
|
||||
|
||||
case "crawl-delay", "crawldelay":
|
||||
// From http://en.wikipedia.org/wiki/Robots_exclusion_standard#Nonstandard_extensions
|
||||
// Several major crawlers support a Crawl-delay parameter, set to the
|
||||
// number of seconds to wait between successive requests to the same server.
|
||||
p.popToken()
|
||||
if cd, e := strconv.ParseFloat(t2, 64); e != nil {
|
||||
return nil, e
|
||||
} else {
|
||||
return &lineInfo{t: lCrawlDelay, k: t1, vf: cd}, nil
|
||||
}
|
||||
}
|
||||
|
||||
// Consume t2 token
|
||||
p.popToken()
|
||||
return &lineInfo{t: lUnknown, k: t1}, nil
|
||||
}
|
||||
|
||||
func (p *parser) popToken() (tok string, ok bool) {
|
||||
tok, ok = p.peekToken()
|
||||
if !ok {
|
||||
return
|
||||
}
|
||||
p.pos++
|
||||
return tok, true
|
||||
}
|
||||
|
||||
func (p *parser) peekToken() (tok string, ok bool) {
|
||||
if p.pos >= len(p.tokens) {
|
||||
return "", false
|
||||
}
|
||||
return p.tokens[p.pos], true
|
||||
}
|
||||
|
|
@ -1,227 +0,0 @@
|
|||
// Package robotstxt implements the robots.txt Exclusion Protocol
|
||||
// as specified in http://www.robotstxt.org/wc/robots.html
|
||||
// with various extensions.
|
||||
package robotstxt
|
||||
|
||||
// Comments explaining the logic are taken from either the Google's spec:
|
||||
// https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"errors"
|
||||
"io/ioutil"
|
||||
"net/http"
|
||||
"regexp"
|
||||
"strconv"
|
||||
"strings"
|
||||
"time"
|
||||
)
|
||||
|
||||
type RobotsData struct {
|
||||
// private
|
||||
groups map[string]*Group
|
||||
allowAll bool
|
||||
disallowAll bool
|
||||
Host string
|
||||
Sitemaps []string
|
||||
}
|
||||
|
||||
type Group struct {
|
||||
rules []*rule
|
||||
Agent string
|
||||
CrawlDelay time.Duration
|
||||
}
|
||||
|
||||
type rule struct {
|
||||
path string
|
||||
allow bool
|
||||
pattern *regexp.Regexp
|
||||
}
|
||||
|
||||
type ParseError struct {
|
||||
Errs []error
|
||||
}
|
||||
|
||||
func newParseError(errs []error) *ParseError {
|
||||
return &ParseError{errs}
|
||||
}
|
||||
|
||||
func (e ParseError) Error() string {
|
||||
var b bytes.Buffer
|
||||
|
||||
b.WriteString("Parse error(s): " + "\n")
|
||||
for _, er := range e.Errs {
|
||||
b.WriteString(er.Error() + "\n")
|
||||
}
|
||||
return b.String()
|
||||
}
|
||||
|
||||
var allowAll = &RobotsData{allowAll: true}
|
||||
var disallowAll = &RobotsData{disallowAll: true}
|
||||
var emptyGroup = &Group{}
|
||||
|
||||
func FromStatusAndBytes(statusCode int, body []byte) (*RobotsData, error) {
|
||||
switch {
|
||||
case statusCode >= 200 && statusCode < 300:
|
||||
return FromBytes(body)
|
||||
|
||||
// From https://developers.google.com/webmasters/control-crawl-index/docs/robots_txt
|
||||
//
|
||||
// Google treats all 4xx errors in the same way and assumes that no valid
|
||||
// robots.txt file exists. It is assumed that there are no restrictions.
|
||||
// This is a "full allow" for crawling. Note: this includes 401
|
||||
// "Unauthorized" and 403 "Forbidden" HTTP result codes.
|
||||
case statusCode >= 400 && statusCode < 500:
|
||||
return allowAll, nil
|
||||
|
||||
// From Google's spec:
|
||||
// Server errors (5xx) are seen as temporary errors that result in a "full
|
||||
// disallow" of crawling.
|
||||
case statusCode >= 500 && statusCode < 600:
|
||||
return disallowAll, nil
|
||||
}
|
||||
|
||||
return nil, errors.New("Unexpected status: " + strconv.Itoa(statusCode))
|
||||
}
|
||||
|
||||
func FromStatusAndString(statusCode int, body string) (*RobotsData, error) {
|
||||
return FromStatusAndBytes(statusCode, []byte(body))
|
||||
}
|
||||
|
||||
func FromResponse(res *http.Response) (*RobotsData, error) {
|
||||
if res == nil {
|
||||
// Edge case, if res is nil, return nil data
|
||||
return nil, nil
|
||||
}
|
||||
buf, e := ioutil.ReadAll(res.Body)
|
||||
if e != nil {
|
||||
return nil, e
|
||||
}
|
||||
return FromStatusAndBytes(res.StatusCode, buf)
|
||||
}
|
||||
|
||||
func FromBytes(body []byte) (r *RobotsData, err error) {
|
||||
var errs []error
|
||||
|
||||
// special case (probably not worth optimization?)
|
||||
trimmed := bytes.TrimSpace(body)
|
||||
if len(trimmed) == 0 {
|
||||
return allowAll, nil
|
||||
}
|
||||
|
||||
sc := newByteScanner("bytes", true)
|
||||
//sc.Quiet = !print_errors
|
||||
sc.feed(body, true)
|
||||
tokens := sc.scanAll()
|
||||
|
||||
// special case worth optimization
|
||||
if len(tokens) == 0 {
|
||||
return allowAll, nil
|
||||
}
|
||||
|
||||
r = &RobotsData{}
|
||||
parser := newParser(tokens)
|
||||
r.groups, r.Host, r.Sitemaps, errs = parser.parseAll()
|
||||
if len(errs) > 0 {
|
||||
return nil, newParseError(errs)
|
||||
}
|
||||
|
||||
return r, nil
|
||||
}
|
||||
|
||||
func FromString(body string) (r *RobotsData, err error) {
|
||||
return FromBytes([]byte(body))
|
||||
}
|
||||
|
||||
func (r *RobotsData) TestAgent(path, agent string) bool {
|
||||
if r.allowAll {
|
||||
return true
|
||||
}
|
||||
if r.disallowAll {
|
||||
return false
|
||||
}
|
||||
|
||||
// Find a group of rules that applies to this agent
|
||||
// From Google's spec:
|
||||
// The user-agent is non-case-sensitive.
|
||||
g := r.FindGroup(agent)
|
||||
return g.Test(path)
|
||||
}
|
||||
|
||||
// FindGroup searches block of declarations for specified user-agent.
|
||||
// From Google's spec:
|
||||
// Only one group of group-member records is valid for a particular crawler.
|
||||
// The crawler must determine the correct group of records by finding the group
|
||||
// with the most specific user-agent that still matches. All other groups of
|
||||
// records are ignored by the crawler. The user-agent is non-case-sensitive.
|
||||
// The order of the groups within the robots.txt file is irrelevant.
|
||||
func (r *RobotsData) FindGroup(agent string) (ret *Group) {
|
||||
var prefixLen int
|
||||
|
||||
agent = strings.ToLower(agent)
|
||||
if ret = r.groups["*"]; ret != nil {
|
||||
// Weakest match possible
|
||||
prefixLen = 1
|
||||
}
|
||||
for a, g := range r.groups {
|
||||
if a != "*" && strings.HasPrefix(agent, a) {
|
||||
if l := len(a); l > prefixLen {
|
||||
prefixLen = l
|
||||
ret = g
|
||||
}
|
||||
}
|
||||
}
|
||||
|
||||
if ret == nil {
|
||||
return emptyGroup
|
||||
}
|
||||
return
|
||||
}
|
||||
|
||||
func (g *Group) Test(path string) bool {
|
||||
if r := g.findRule(path); r != nil {
|
||||
return r.allow
|
||||
}
|
||||
|
||||
// From Google's spec:
|
||||
// By default, there are no restrictions for crawling for the designated crawlers.
|
||||
return true
|
||||
}
|
||||
|
||||
// From Google's spec:
|
||||
// The path value is used as a basis to determine whether or not a rule applies
|
||||
// to a specific URL on a site. With the exception of wildcards, the path is
|
||||
// used to match the beginning of a URL (and any valid URLs that start with the
|
||||
// same path).
|
||||
//
|
||||
// At a group-member level, in particular for allow and disallow directives,
|
||||
// the most specific rule based on the length of the [path] entry will trump
|
||||
// the less specific (shorter) rule. The order of precedence for rules with
|
||||
// wildcards is undefined.
|
||||
func (g *Group) findRule(path string) (ret *rule) {
|
||||
var prefixLen int
|
||||
|
||||
for _, r := range g.rules {
|
||||
if r.pattern != nil {
|
||||
if r.pattern.MatchString(path) {
|
||||
// Consider this a match equal to the length of the pattern.
|
||||
// From Google's spec:
|
||||
// The order of precedence for rules with wildcards is undefined.
|
||||
if l := len(r.pattern.String()); l > prefixLen {
|
||||
prefixLen = len(r.pattern.String())
|
||||
ret = r
|
||||
}
|
||||
}
|
||||
} else if r.path == "/" && prefixLen == 0 {
|
||||
// Weakest match possible
|
||||
prefixLen = 1
|
||||
ret = r
|
||||
} else if strings.HasPrefix(path, r.path) {
|
||||
if l := len(r.path); l > prefixLen {
|
||||
prefixLen = l
|
||||
ret = r
|
||||
}
|
||||
}
|
||||
}
|
||||
return
|
||||
}
|
||||
|
|
@ -1,185 +0,0 @@
|
|||
package robotstxt
|
||||
|
||||
import (
|
||||
"bytes"
|
||||
"fmt"
|
||||
"go/token"
|
||||
"os"
|
||||
"sync"
|
||||
"unicode/utf8"
|
||||
)
|
||||
|
||||
type byteScanner struct {
|
||||
pos token.Position
|
||||
buf []byte
|
||||
ErrorCount int
|
||||
ch rune
|
||||
Quiet bool
|
||||
keyTokenFound bool
|
||||
lastChunk bool
|
||||
}
|
||||
|
||||
const tokEOL = "\n"
|
||||
|
||||
var WhitespaceChars = []rune{' ', '\t', '\v'}
|
||||
var tokBuffers = sync.Pool{New: func() interface{} { return bytes.NewBuffer(make([]byte, 32)) }}
|
||||
|
||||
func newByteScanner(srcname string, quiet bool) *byteScanner {
|
||||
return &byteScanner{
|
||||
Quiet: quiet,
|
||||
ch: -1,
|
||||
pos: token.Position{Filename: srcname},
|
||||
}
|
||||
}
|
||||
|
||||
func (s *byteScanner) feed(input []byte, end bool) {
|
||||
s.buf = input
|
||||
s.pos.Offset = 0
|
||||
s.pos.Line = 1
|
||||
s.pos.Column = 1
|
||||
s.lastChunk = end
|
||||
|
||||
// Read first char into look-ahead buffer `s.ch`.
|
||||
if !s.nextChar() {
|
||||
return
|
||||
}
|
||||
|
||||
// Skip UTF-8 byte order mark
|
||||
if s.ch == 65279 {
|
||||
s.nextChar()
|
||||
s.pos.Column = 1
|
||||
}
|
||||
}
|
||||
|
||||
func (s *byteScanner) GetPosition() token.Position {
|
||||
return s.pos
|
||||
}
|
||||
|
||||
func (s *byteScanner) scan() string {
|
||||
// Note Offset > len, not >=, so we can scan last character.
|
||||
if s.lastChunk && s.pos.Offset > len(s.buf) {
|
||||
return ""
|
||||
}
|
||||
|
||||
s.skipSpace()
|
||||
|
||||
if s.ch == -1 {
|
||||
return ""
|
||||
}
|
||||
|
||||
// EOL
|
||||
if s.isEol() {
|
||||
s.keyTokenFound = false
|
||||
// skip subsequent newline chars
|
||||
for s.ch != -1 && s.isEol() {
|
||||
s.nextChar()
|
||||
}
|
||||
// emit newline as separate token
|
||||
return tokEOL
|
||||
}
|
||||
|
||||
// skip comments
|
||||
if s.ch == '#' {
|
||||
s.keyTokenFound = false
|
||||
s.skipUntilEol()
|
||||
if s.ch == -1 {
|
||||
return ""
|
||||
}
|
||||
// emit newline as separate token
|
||||
return tokEOL
|
||||
}
|
||||
|
||||
// else we found something
|
||||
tok := tokBuffers.Get().(*bytes.Buffer)
|
||||
defer tokBuffers.Put(tok)
|
||||
tok.Reset()
|
||||
tok.WriteRune(s.ch)
|
||||
s.nextChar()
|
||||
for s.ch != -1 && !s.isSpace() && !s.isEol() {
|
||||
// Do not consider ":" to be a token separator if a first key token
|
||||
// has already been found on this line (avoid cutting an absolute URL
|
||||
// after the "http:")
|
||||
if s.ch == ':' && !s.keyTokenFound {
|
||||
s.nextChar()
|
||||
s.keyTokenFound = true
|
||||
break
|
||||
}
|
||||
|
||||
tok.WriteRune(s.ch)
|
||||
s.nextChar()
|
||||
}
|
||||
return tok.String()
|
||||
}
|
||||
|
||||
func (s *byteScanner) scanAll() []string {
|
||||
results := make([]string, 0, 64) // random guess of average tokens length
|
||||
for {
|
||||
token := s.scan()
|
||||
if token != "" {
|
||||
results = append(results, token)
|
||||
} else {
|
||||
break
|
||||
}
|
||||
}
|
||||
return results
|
||||
}
|
||||
|
||||
func (s *byteScanner) error(pos token.Position, msg string) {
|
||||
s.ErrorCount++
|
||||
if !s.Quiet {
|
||||
fmt.Fprintf(os.Stderr, "robotstxt from %s: %s\n", pos.String(), msg)
|
||||
}
|
||||
}
|
||||
|
||||
func (s *byteScanner) isEol() bool {
|
||||
return s.ch == '\n' || s.ch == '\r'
|
||||
}
|
||||
|
||||
func (s *byteScanner) isSpace() bool {
|
||||
for _, r := range WhitespaceChars {
|
||||
if s.ch == r {
|
||||
return true
|
||||
}
|
||||
}
|
||||
return false
|
||||
}
|
||||
|
||||
func (s *byteScanner) skipSpace() {
|
||||
for s.ch != -1 && s.isSpace() {
|
||||
s.nextChar()
|
||||
}
|
||||
}
|
||||
|
||||
func (s *byteScanner) skipUntilEol() {
|
||||
for s.ch != -1 && !s.isEol() {
|
||||
s.nextChar()
|
||||
}
|
||||
// skip subsequent newline chars
|
||||
for s.ch != -1 && s.isEol() {
|
||||
s.nextChar()
|
||||
}
|
||||
}
|
||||
|
||||
// Reads next Unicode char.
|
||||
func (s *byteScanner) nextChar() bool {
|
||||
if s.pos.Offset >= len(s.buf) {
|
||||
s.ch = -1
|
||||
return false
|
||||
}
|
||||
s.pos.Column++
|
||||
if s.ch == '\n' {
|
||||
s.pos.Line++
|
||||
s.pos.Column = 1
|
||||
}
|
||||
r, w := rune(s.buf[s.pos.Offset]), 1
|
||||
if r >= 0x80 {
|
||||
r, w = utf8.DecodeRune(s.buf[s.pos.Offset:])
|
||||
if r == utf8.RuneError && w == 1 {
|
||||
s.error(s.pos, "illegal UTF-8 encoding")
|
||||
}
|
||||
}
|
||||
s.pos.Column++
|
||||
s.pos.Offset += w
|
||||
s.ch = r
|
||||
return true
|
||||
}
|
||||
|
|
@ -65,8 +65,6 @@ github.com/ChrisTrenkamp/goxpath/xconst
|
|||
github.com/NaverCloudPlatform/ncloud-sdk-go-v2/hmac
|
||||
github.com/NaverCloudPlatform/ncloud-sdk-go-v2/ncloud
|
||||
github.com/NaverCloudPlatform/ncloud-sdk-go-v2/services/server
|
||||
# github.com/PuerkitoBio/goquery v1.5.0
|
||||
github.com/PuerkitoBio/goquery
|
||||
# github.com/StackExchange/wmi v0.0.0-20190523213315-cbe66965904d
|
||||
github.com/StackExchange/wmi
|
||||
# github.com/Telmate/proxmox-api-go v0.0.0-20200715182505-ec97c70ba887
|
||||
|
|
@ -88,12 +86,6 @@ github.com/aliyun/alibaba-cloud-sdk-go/services/ecs
|
|||
github.com/aliyun/alibaba-cloud-sdk-go/services/ram
|
||||
# github.com/aliyun/aliyun-oss-go-sdk v0.0.0-20170113022742-e6dbea820a9f
|
||||
github.com/aliyun/aliyun-oss-go-sdk/oss
|
||||
# github.com/andybalholm/cascadia v1.0.0
|
||||
github.com/andybalholm/cascadia
|
||||
# github.com/antchfx/htmlquery v1.0.0
|
||||
github.com/antchfx/htmlquery
|
||||
# github.com/antchfx/xmlquery v1.0.0
|
||||
github.com/antchfx/xmlquery
|
||||
# github.com/antchfx/xpath v0.0.0-20170728053731-b5c552e1acbd
|
||||
github.com/antchfx/xpath
|
||||
# github.com/antchfx/xquery v0.0.0-20170730121040-eb8c3c172607
|
||||
|
|
@ -233,10 +225,6 @@ github.com/gobwas/glob/syntax/ast
|
|||
github.com/gobwas/glob/syntax/lexer
|
||||
github.com/gobwas/glob/util/runes
|
||||
github.com/gobwas/glob/util/strings
|
||||
# github.com/gocolly/colly v1.2.0
|
||||
github.com/gocolly/colly
|
||||
github.com/gocolly/colly/debug
|
||||
github.com/gocolly/colly/storage
|
||||
# github.com/gofrs/flock v0.7.1 => github.com/azr/flock v0.0.0-20190823144736-958d66434653
|
||||
github.com/gofrs/flock
|
||||
# github.com/gofrs/uuid v3.2.0+incompatible
|
||||
|
|
@ -424,8 +412,6 @@ github.com/jstemmer/go-junit-report/formatter
|
|||
github.com/jstemmer/go-junit-report/parser
|
||||
# github.com/kardianos/osext v0.0.0-20170510131534-ae77be60afb1
|
||||
github.com/kardianos/osext
|
||||
# github.com/kennygrant/sanitize v1.2.4
|
||||
github.com/kennygrant/sanitize
|
||||
# github.com/klauspost/compress v0.0.0-20160131094358-f86d2e6d8a77
|
||||
github.com/klauspost/compress/flate
|
||||
# github.com/klauspost/cpuid v0.0.0-20160106104451-349c67577817
|
||||
|
|
@ -518,8 +504,6 @@ github.com/profitbricks/profitbricks-sdk-go
|
|||
github.com/renstrom/fuzzysearch/fuzzy
|
||||
# github.com/ryanuber/go-glob v1.0.0
|
||||
github.com/ryanuber/go-glob
|
||||
# github.com/saintfish/chardet v0.0.0-20120816061221-3af4cd4741ca
|
||||
github.com/saintfish/chardet
|
||||
# github.com/satori/go.uuid v1.2.0
|
||||
github.com/satori/go.uuid
|
||||
# github.com/scaleway/scaleway-cli v0.0.0-20180921094345-7b12c9699d70
|
||||
|
|
@ -540,8 +524,6 @@ github.com/sirupsen/logrus
|
|||
# github.com/stretchr/testify v1.5.1
|
||||
github.com/stretchr/testify/assert
|
||||
github.com/stretchr/testify/require
|
||||
# github.com/temoto/robotstxt v1.1.1
|
||||
github.com/temoto/robotstxt
|
||||
# github.com/tencentcloud/tencentcloud-sdk-go v3.0.155+incompatible
|
||||
github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/common
|
||||
github.com/tencentcloud/tencentcloud-sdk-go/tencentcloud/common/errors
|
||||
|
|
|
|||
Loading…
Reference in New Issue